© 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. 27953
    Prev
    Next
    INDEX
    Explanations

    instances of the word "said" and related forms

    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
    362
    +0.13
    0.6%
    472
    +0.13
    0.6%
    380
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    446
    +0.13
    0.02
    159
    +0.13
    0.03
    362
    +0.12
    0.04
    Negative Logits
    ADRA
    -0.84
    姫
    -0.84
    lished
    -0.78
    ntil
    -0.76
    accompanied
    -0.75
    à¹
    -0.73
    âĺ
    -0.69
     Pwr
    -0.69
     Zup
    -0.69
    Õ
    -0.69
    POSITIVE LOGITS
     aforementioned
    0.79
     latter
    0.79
     pesky
    0.79
     same
    0.78
    selves
    0.76
     situation
    0.74
     exact
    0.74
     predicament
    0.72
     shores
    0.71
     latest
    0.70
    Activations Density 0.398%

    No Known Activations