© 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. 3526
    Prev
    Next
    INDEX
    Explanations

    scientific terms and concepts in research contexts

    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
    497
    +0.24
    1.1%
    420
    +0.13
    0.6%
    459
    +0.12
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    497
    +0.24
    -0.04
    64
    +0.13
    -0.18
    524
    +0.12
    0.13
    Negative Logits
    ukong
    -0.84
     Wade
    -0.74
     Dunham
    -0.70
    claw
    -0.69
     COUNTY
    -0.69
    lund
    -0.68
    Instance
    -0.67
    ojure
    -0.66
     Bundy
    -0.65
    abwe
    -0.65
    POSITIVE LOGITS
     requirement
    0.75
     guideline
    0.68
    sylv
    0.65
    ventions
    0.63
    oral
    0.63
     effic
    0.61
     decrease
    0.61
     modifier
    0.60
    alities
    0.60
     transparent
    0.60
    Activations Density 13.057%

    No Known Activations