© 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. Attention Out - 32k
    5. 3-ATT_32K-OAI
    6. 3627
    Prev
    Next
    INDEX
    Explanations

    conjunctions and connectors that denote relationships among elements in a discussion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-att_32k-oai
    Configuration
    jbloom/GPT2-Small-OAI-v5-32k-attn-out-SAEs/v5_32k_layer_3
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.3.hook_attn_out
    Hook Layer
    3
    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
    179
    +0.13
    0.6%
    320
    +0.12
    0.6%
    220
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    179
    +0.13
    0.10
    155
    +0.12
    0.06
    320
    +0.12
    0.03
    Negative Logits
    ":"/
    -0.71
    =-=-=-=-=-=-=-=-
    -0.68
    idated
    -0.68
    Reward
    -0.63
    :/
    -0.62
    »Ĵ
    -0.60
    Repl
    -0.59
    cest
    -0.59
    SHIP
    -0.58
     certs
    -0.58
    POSITIVE LOGITS
    pixel
    0.83
     convol
    0.77
    zona
    0.72
     skelet
    0.70
     orbits
    0.68
    oglu
    0.66
    riots
    0.66
    awks
    0.65
    ',"
    0.64
    NSA
    0.64
    Activations Density 5.941%

    No Known Activations