© 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
    3. OpenAI · Sparse Autoencoder for GPT2-Small - v5 2024
    5. GPT2-Small
    7. Attention Out - 32k
    9. 3-ATT_32K-OAI
    11. 3832
    Prev
    Next
    INDEX
    Explanations

    programming language syntax elements and structure

    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
    36
    +0.15
    0.7%
    71
    +0.14
    0.7%
    413
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    36
    +0.15
    0.04
    323
    +0.14
    0.03
    413
    +0.11
    0.03
    Negative Logits
    igham
    -0.80
    paces
    -0.69
    hire
    -0.67
    opian
    -0.64
    UAL
    -0.63
    abase
    -0.62
    ouver
    -0.61
     remotely
    -0.61
    rays
    -0.60
     apartheid
    -0.59
    POSITIVE LOGITS
    ĵĺ
    0.70
    ér
    0.67
    noxious
    0.61
    alogue
    0.60
     loader
    0.59
     cand
    0.58
    RET
    0.58
     poop
    0.58
    ogram
    0.57
    HM
    0.57
    Activations Density 0.132%

    No Known Activations