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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. OpenAI · Sparse Autoencoder for GPT2-Small - v5 2024
    3. GPT2-Small
    4. Residual Post - 32k
    5. 8-RES_POST_32K-OAI
    6. 5250
    Prev
    Next
    INDEX
    Explanations

    mentions of mammals and related animals

    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
    163
    +0.10
    0.5%
    626
    +0.10
    0.5%
    116
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    232
    +0.10
    0.02
    103
    +0.10
    0.02
    314
    +0.10
    0.00
    Negative Logits
    nces
    -0.62
    âĢ¢âĢ¢
    -0.61
    roller
    -0.60
    holders
    -0.57
    fast
    -0.56
     Grounds
    -0.56
    voy
    -0.56
    Hill
    -0.56
    ching
    -0.56
     Maduro
    -0.56
    POSITIVE LOGITS
    olit
    1.08
    obil
    0.93
    arella
    0.93
    arsh
    0.89
    oths
    0.88
    uth
    0.87
    ateur
    0.86
    agic
    0.86
    essage
    0.86
    ush
    0.85
    Activations Density 0.140%

    No Known Activations