© 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. 3988
    Prev
    Next
    INDEX
    Explanations

    references to individuals or groups of people

    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
    218
    +0.14
    0.6%
    567
    +0.12
    0.5%
    509
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    64
    +0.14
    -0.04
    579
    +0.12
    0.03
    91
    +0.10
    0.03
    Negative Logits
    =]
    -0.79
    wald
    -0.73
     Dart
    -0.72
    enegger
    -0.71
    platform
    -0.70
    ranch
    -0.69
    shoot
    -0.69
    eries
    -0.69
    cill
    -0.68
    icer
    -0.68
    POSITIVE LOGITS
     incap
    0.75
     allergic
    0.73
     witnessing
    0.72
     imperson
    0.71
     misunderstand
    0.71
     pronoun
    0.69
     dysph
    0.68
     identifiable
    0.66
     mishand
    0.66
     breastfeeding
    0.64
    Activations Density 1.392%

    No Known Activations