© 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. 26884
    Prev
    Next
    INDEX
    Explanations

    terms related to desolation or destruction

    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
    288
    +0.12
    0.6%
    615
    +0.12
    0.5%
    658
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    288
    +0.12
    0.02
    232
    +0.12
    0.01
    441
    +0.09
    0.01
    Negative Logits
    manship
    -0.90
     enqu
    -0.67
    Reviewer
    -0.66
    peat
    -0.62
     Dragonbound
    -0.62
     IPM
    -0.61
     tiss
    -0.61
     Osw
    -0.61
     examiner
    -0.60
     Lans
    -0.59
    POSITIVE LOGITS
    roying
    1.62
    ruct
    1.51
    inations
    1.31
    ination
    1.26
    iny
    1.25
    ruction
    1.20
    ined
    1.16
    abil
    1.10
    itute
    1.05
    iral
    0.97
    Activations Density 0.053%

    No Known Activations