© 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
    3. OpenAI · Sparse Autoencoder for GPT2-Small - v5 2024
    5. GPT2-Small
    7. Attention Out - 32k
    9. 3-ATT_32K-OAI
    11. 3290
    Prev
    Next
    INDEX
    Explanations

    names of scientific journals

    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
    +0.16
    0.7%
    71
    +0.12
    0.5%
    107
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    325
    +0.16
    0.04
    649
    +0.12
    0.03
    317
    +0.11
    0.04
    Negative Logits
     reserv
    -0.68
     typo
    -0.66
     lim
    -0.66
     assassinate
    -0.63
     stockp
    -0.62
     whistleblower
    -0.61
    âĦ¢:
    -0.61
     beard
    -0.61
     yourselves
    -0.59
     SEAL
    -0.59
    POSITIVE LOGITS
    onica
    0.97
    psy
    0.80
    pport
    0.77
     Behavior
    0.74
    yssey
    0.71
    entimes
    0.70
    ournal
    0.70
    Soc
    0.69
    Tracker
    0.68
    doi
    0.67
    Activations Density 1.012%

    No Known Activations