© 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. 3637
    Prev
    Next
    INDEX
    Explanations

    programming-related terms and concepts associated with algorithms and data structures

    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
    458
    +0.12
    0.5%
    410
    +0.11
    0.5%
    427
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    738
    +0.12
    0.07
    289
    +0.11
    0.05
    731
    +0.10
    0.04
    Negative Logits
    wagen
    -0.81
    hov
    -0.80
    enza
    -0.76
    idges
    -0.73
    ucci
    -0.70
    axter
    -0.70
    inks
    -0.70
    ideos
    -0.68
    oppers
    -0.67
    istor
    -0.67
    POSITIVE LOGITS
     contextual
    0.79
     Proxy
    0.70
    ¿½
    0.69
     judgment
    0.67
     ACS
    0.66
     Context
    0.65
     situational
    0.64
    ¥µ
    0.63
    ²¾
    0.61
     relevant
    0.60
    Activations Density 1.419%

    No Known Activations