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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 4333
    Prev
    Next
    INDEX
    Explanations

    mentions of geographic locations and significant environmental features

    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
    570
    +0.12
    0.6%
    51
    +0.11
    0.5%
    113
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    330
    +0.12
    0.05
    688
    +0.11
    0.04
    113
    +0.11
    0.04
    Negative Logits
    ronics
    -0.76
    ©¶æ¥µ
    -0.71
    Assembly
    -0.70
     Nobel
    -0.70
     portfolios
    -0.68
     photoc
    -0.66
    Accessory
    -0.66
     Reich
    -0.65
     Cabinet
    -0.63
     discretion
    -0.63
    POSITIVE LOGITS
    waters
    0.91
    isSpecialOrderable
    0.83
     east
    0.77
     lakes
    0.77
     Gibraltar
    0.76
    Ê
    0.75
     Himal
    0.74
     Basin
    0.74
    near
    0.73
    upt
    0.73
    Activations Density 1.532%

    No Known Activations