© 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
    3. OpenAI · Sparse Autoencoder for GPT2-Small - v5 2024
    5. GPT2-Small
    7. Residual Post - 32k
    9. 8-RES_POST_32K-OAI
    11. 6162
    Prev
    Next
    INDEX
    Explanations

    statistical data and numerical comparisons

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_post_32k-oai
    Configuration
    jbloom/GPT2-Small-OAI-v5-32k-resid-post-SAEs/v5_32k_layer_8.pt
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    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
    176
    +0.13
    0.6%
    373
    +0.12
    0.5%
    118
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    475
    +0.13
    0.08
    326
    +0.12
    0.08
    493
    +0.10
    0.06
    Negative Logits
    ©¶æ
    -0.75
     skelet
    -0.72
     pse
    -0.62
    wcsstore
    -0.61
     )]
    -0.59
    £ı
    -0.56
     referen
    -0.56
     tyr
    -0.55
     clipboard
    -0.54
     surv
    -0.53
    POSITIVE LOGITS
    >.
    1.45
    .).
    1.44
    ).
    1.30
    '.
    1.29
    +.
    1.23
    ].
    1.20
    ".
    1.20
    $.
    1.16
    %.
    1.15
    }.
    1.12
    Activations Density 0.808%

    No Known Activations