© 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. 3749
    Prev
    Next
    INDEX
    Explanations

    expressions of personal beliefs and opinions

    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
    +0.15
    0.7%
    265
    +0.10
    0.5%
    500
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    756
    +0.15
    0.11
    351
    +0.10
    0.05
    380
    +0.09
    0.07
    Negative Logits
    paces
    -0.88
    eton
    -0.80
    iosyncr
    -0.77
    izontal
    -0.76
    otypes
    -0.72
    omorphic
    -0.72
    ayers
    -0.71
    ographics
    -0.71
    umer
    -0.70
    fram
    -0.69
    POSITIVE LOGITS
     adultery
    0.81
     perjury
    0.80
     treason
    0.80
     sorcerer
    0.78
     brig
    0.78
     treacher
    0.77
     persecution
    0.77
     incap
    0.76
     princip
    0.76
     martyr
    0.75
    Activations Density 3.760%

    No Known Activations