© 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. 3571
    Prev
    Next
    INDEX
    Explanations

    references to familial or close relationships

    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
    138
    +0.82
    6.2%
    745
    +0.10
    0.7%
    218
    +0.08
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    266
    +0.82
    0.07
    101
    +0.10
    0.01
    99
    +0.08
    0.01
    Negative Logits
    )",
    -0.68
     ..."
    -0.63
    )"
    -0.60
     âĢ¦"
    -0.59
    )."
    -0.56
     distingu
    -0.52
    ĸļ
    -0.52
    ?'"
    -0.51
     fundament
    -0.51
    ),"
    -0.50
    POSITIVE LOGITS
    Ill
    0.43
    iling
    0.41
    Warning
    0.40
     "
    0.40
    iled
    0.37
    brew
    0.37
    go
    0.36
    lat
    0.35
    screen
    0.35
    PA
    0.34
    Activations Density 0.510%

    No Known Activations