© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 4186
    Prev
    Next
    INDEX
    Explanations

    statistics and opinions related to public perception of political issues and figures

    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
    684
    +0.14
    0.6%
    497
    +0.13
    0.6%
    279
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    401
    +0.14
    0.14
    316
    +0.13
    0.10
    710
    +0.10
    0.10
    Negative Logits
     extrad
    -0.82
     boiler
    -0.81
    oop
    -0.76
     manufact
    -0.72
    leases
    -0.71
     outlaw
    -0.69
     prototypes
    -0.69
    rooms
    -0.69
     prolifer
    -0.68
     reopen
    -0.67
    POSITIVE LOGITS
     Gallup
    0.85
     polled
    0.80
    vote
    0.79
     Voting
    0.79
     Conversation
    0.77
     Vote
    0.77
    Vote
    0.74
    Score
    0.73
    Ranked
    0.70
     (+
    0.70
    Activations Density 10.594%

    No Known Activations