© 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. 5282
    Prev
    Next
    INDEX
    Explanations

    names and terms related to people and their positive contributions or characteristics

    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
    497
    +0.14
    0.6%
    245
    +0.13
    0.6%
    357
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.14
    0.06
    232
    +0.13
    0.06
    284
    +0.12
    0.04
    Negative Logits
    EngineDebug
    -0.69
     bells
    -0.68
     crap
    -0.66
     NETWORK
    -0.63
     DEAD
    -0.62
     revival
    -0.62
     bandwagon
    -0.61
     CODE
    -0.61
    ãĥīãĥ©ãĤ´ãĥ³
    -0.61
    =>
    -0.60
    POSITIVE LOGITS
    za
    1.00
    ith
    0.90
    nu
    0.87
    uf
    0.86
    asa
    0.84
    udo
    0.80
    xa
    0.79
    azel
    0.79
    arna
    0.79
    aqu
    0.79
    Activations Density 0.185%

    No Known Activations