© 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. 4008
    Prev
    Next
    INDEX
    Explanations

    statements related to event announcements and operational updates

    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
    756
    +0.13
    0.6%
    736
    +0.13
    0.6%
    680
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    736
    +0.13
    0.19
    86
    +0.13
    0.22
    756
    +0.10
    0.23
    Negative Logits
    âĢ¦)
    -0.69
    âĢIJ
    -0.69
    etimes
    -0.64
    space
    -0.63
     unaccount
    -0.63
    pol
    -0.62
    global
    -0.62
    soft
    -0.62
    .).
    -0.60
    foreign
    -0.60
    POSITIVE LOGITS
    nesday
    0.71
    enegger
    0.71
    ATES
    0.70
    icip
    0.70
     concess
    0.69
    ORK
    0.68
    eto
    0.68
    mediately
    0.65
     withd
    0.65
     NAV
    0.65
    Activations Density 18.594%

    No Known Activations