© 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. 3761
    Prev
    Next
    INDEX
    Explanations

    references to darkness or dark-themed concepts

    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
    494
    +0.11
    0.5%
    239
    +0.10
    0.5%
    325
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    548
    +0.11
    0.02
    35
    +0.10
    0.02
    325
    +0.10
    0.03
    Negative Logits
    reciation
    -0.86
    Ĥ¬
    -0.80
    cknowled
    -0.77
    anchester
    -0.74
    Guy
    -0.72
     rebutt
    -0.71
    ħĭ
    -0.70
    arge
    -0.70
    è¦ļéĨĴ
    -0.67
     Curry
    -0.67
    POSITIVE LOGITS
    iosity
    0.83
     clouds
    0.81
    complex
    0.77
     emanating
    0.75
     flickering
    0.72
     reflections
    0.72
     priv
    0.71
     looms
    0.70
     abyss
    0.69
     rav
    0.69
    Activations Density 0.742%

    No Known Activations