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

    Neuronpedia

    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. 29336
    Prev
    Next
    INDEX
    Explanations

    bracketed references or citations

    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
    206
    +0.09
    0.4%
    360
    +0.09
    0.4%
    303
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    92
    +0.09
    0.03
    517
    +0.09
    0.02
    720
    +0.09
    0.03
    Negative Logits
    ,
    -0.66
    (&
    -0.63
     (>
    -0.63
    ãĥŃ
    -0.59
    -+-+
    -0.58
     ASUS
    -0.57
    ãĤ´ãĥ³
    -0.56
    %%
    -0.56
     (%
    -0.54
    zu
    -0.53
    POSITIVE LOGITS
    ...]
    0.91
    selves
    0.88
    thumbnails
    0.86
    ],
    0.82
    cause
    0.80
    ."[
    0.79
    â̦]
    0.77
    ".[
    0.77
     ],
    0.76
    ].
    0.73
    Activations Density 0.423%

    No Known Activations