© 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. 4267
    Prev
    Next
    INDEX
    Explanations

    details related to conversations and discussions about various topics

    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
    470
    +0.11
    0.5%
    501
    +0.10
    0.4%
    57
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    491
    +0.11
    0.12
    59
    +0.10
    0.15
    474
    +0.10
    0.11
    Negative Logits
    ynthesis
    -0.94
    forestation
    -0.82
    kefeller
    -0.80
    ortality
    -0.77
     rebuilt
    -0.76
     domest
    -0.75
    cair
    -0.75
    aceae
    -0.74
     steril
    -0.74
    letal
    -0.73
    POSITIVE LOGITS
     interviewer
    1.04
     replies
    0.98
     answering
    0.97
     listener
    0.97
    answered
    0.94
    answer
    0.91
     banter
    0.90
    talking
    0.90
     microphone
    0.89
     microphones
    0.89
    Activations Density 29.046%

    No Known Activations