© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. OpenAI · Sparse Autoencoder for GPT2-Small - v5 2024
    3. GPT2-Small
    4. Residual Post - 32k
    5. 10-RES_POST_32K-OAI
    6. 31069
    Prev
    Next
    INDEX
    Explanations

    emotions and personal reflections related to guilt, confusion, and frustration

    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
    +0.13
    0.6%
    554
    +0.12
    0.5%
    125
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    759
    +0.13
    0.10
    125
    +0.12
    0.06
    351
    +0.11
    0.08
    Negative Logits
     Pastebin
    -0.75
    ials
    -0.73
    cki
    -0.65
    framework
    -0.63
    pmwiki
    -0.61
    lation
    -0.60
    igree
    -0.60
    />
    -0.60
     yourselves
    -0.60
    eve
    -0.59
    POSITIVE LOGITS
     profoundly
    1.08
     irresist
    0.98
     greatly
    0.98
     deeply
    0.93
     enormously
    0.93
     dearly
    0.93
     immensely
    0.87
     psychologically
    0.86
     acutely
    0.86
     spiritually
    0.84
    Activations Density 1.297%

    No Known Activations