© 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. 3892
    Prev
    Next
    INDEX
    Explanations

    phrases related to biological threats and security concerns

    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
    91
    +0.11
    0.5%
    462
    +0.11
    0.5%
    270
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    270
    +0.11
    0.15
    91
    +0.11
    0.15
    505
    +0.10
    0.10
    Negative Logits
    etheless
    -0.92
    eatures
    -0.73
    xtap
    -0.72
     partName
    -0.69
    hement
    -0.67
     Quart
    -0.67
    clair
    -0.66
     clust
    -0.65
    NetMessage
    -0.65
    udden
    -0.65
    POSITIVE LOGITS
    versive
    0.68
     dope
    0.68
     Afgh
    0.68
     Osc
    0.67
     vet
    0.66
    uana
    0.63
    dfx
    0.63
    milo
    0.62
     illegally
    0.60
     paradise
    0.60
    Activations Density 9.888%

    No Known Activations