© 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. 10-RES_POST_32K-OAI
    11. 28247
    Prev
    Next
    INDEX
    Explanations

    prepositions

    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
    64
    +0.15
    0.7%
    87
    +0.13
    0.6%
    400
    +0.11
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    481
    +0.15
    0.16
    608
    +0.13
    0.21
    362
    +0.11
    0.18
    Negative Logits
    cule
    -0.55
    ãĤ´ãĥ³
    -0.53
    gru
    -0.52
     Royale
    -0.51
    Po
    -0.51
    alan
    -0.50
     Bagg
    -0.50
    ex
    -0.50
    ãĤ¹ãĥĪ
    -0.50
    ule
    -0.50
    POSITIVE LOGITS
    ?).
    0.89
    )?
    0.88
    ?),
    0.81
     hers
    0.74
    ?'"
    0.72
     yourselves
    0.71
     landfall
    0.69
     theirs
    0.68
    !).
    0.65
    ?)
    0.65
    Activations Density 2.269%

    No Known Activations