© 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. 3591
    Prev
    Next
    INDEX
    Explanations

    actions or activities that occur frequently or on a regular basis

    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
    71
    +0.13
    0.6%
    9
    +0.10
    0.5%
    65
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    609
    +0.13
    0.03
    554
    +0.10
    0.04
    301
    +0.09
    0.02
    Negative Logits
     merging
    -0.69
     unification
    -0.65
     Aly
    -0.62
     feeling
    -0.61
     radius
    -0.61
     realization
    -0.60
     belongs
    -0.60
     destiny
    -0.60
     detachment
    -0.59
     brothers
    -0.59
    POSITIVE LOGITS
     nightly
    0.80
    à¨
    0.75
    ailable
    0.69
    lished
    0.69
     quarterly
    0.68
     tabl
    0.68
     regularly
    0.67
    rences
    0.66
     pest
    0.66
    azines
    0.66
    Activations Density 0.325%

    No Known Activations