© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenAI · Sparse Autoencoder for GPT2-Small - v5 2024
    5. GPT2-Small
    7. Residual Post - 32k
    9. 10-RES_POST_32K-OAI
    11. 27592
    Prev
    Next
    INDEX
    Explanations

    concepts related to psychological defense mechanisms and coping strategies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res_post_32k-oai
    Configuration
    jbloom/GPT2-Small-OAI-v5-32k-resid-post-SAEs/v5_32k_layer_10.pt
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    standard
    Context Size
    64
    Dataset
    Skylion007/openwebtext
    Activation Function
    topk
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Neuron Alignment
    Index
    Value
    % of L₁
    759
    +0.15
    0.7%
    125
    +0.11
    0.5%
    660
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    759
    +0.15
    0.13
    271
    +0.11
    0.12
    351
    +0.10
    0.12
    Negative Logits
     ---------
    -0.72
    SourceFile
    -0.71
    anka
    -0.70
    ospons
    -0.68
     Showdown
    -0.67
     Illegal
    -0.66
     BaseType
    -0.65
     Rankings
    -0.65
     VID
    -0.64
     DOJ
    -0.64
    POSITIVE LOGITS
     consciously
    1.28
     unconsciously
    1.26
     inward
    1.25
     emotionally
    1.20
     subconscious
    1.12
     psychologically
    1.11
     mentally
    1.10
     intellectually
    1.05
     spiritually
    1.04
     conscious
    0.99
    Activations Density 2.213%

    No Known Activations