Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenAI · Sparse Autoencoder for GPT2-Small - v5 2024
    3. GPT2-Small
    4. Attention Out - 128k
    5. 0-ATT_128K-OAI
    6. 13589
    Prev
    Next
    INDEX
    Explanations

    file paths and commands related to system administration

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    jbloom/GPT2-Small-OAI-v5-128k-attn-out-SAEs/v5_128k_layer_0
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    131,072
    Data Type
    torch.float32
    Hook Name
    blocks.0.hook_attn_out
    Hook Layer
    0
    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
    742
    +0.18
    1.3%
    1
    +0.17
    1.2%
    26
    +0.14
    1.0%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    600
    +0.18
    0.01
    742
    +0.17
    0.01
    323
    +0.14
    0.01
    Negative Logits
    ablishment
    -0.82
    ³³³³³³³³
    -0.77
     CLSID
    -0.75
     recall
    -0.74
    ³³³³³³³³³³³³³³³³
    -0.70
    """
    -0.70
     Cyr
    -0.68
    rolet
    -0.67
    ³³³
    -0.66
    aroo
    -0.66
    POSITIVE LOGITS
    Laughs
    0.78
    bial
    0.77
    agues
    0.77
    Agent
    0.76
    images
    0.75
    Pg
    0.74
    asma
    0.74
    cod
    0.73
    Cod
    0.72
    fac
    0.71
    Activations Density 0.036%

    No Known Activations