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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 6449
    Prev
    Next
    INDEX
    Explanations

    terms related to registration or official status

    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
    311
    +0.28
    2.1%
    385
    +0.27
    2.0%
    710
    +0.18
    1.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    746
    +0.28
    0.00
    699
    +0.27
    0.00
    21
    +0.18
    0.00
    Negative Logits
     ãĤµãĥ¼ãĥĨãĤ£ãĥ¯ãĥ³
    -0.76
     Bulgar
    -0.75
    ãĤ¡
    -0.73
     afar
    -0.70
     Helsinki
    -0.69
     Antar
    -0.69
     NCT
    -0.64
     flick
    -0.63
    FY
    -0.62
     curv
    -0.61
    POSITIVE LOGITS
    wcsstore
    0.98
    Reviewer
    0.91
    ourke
    0.89
    htaking
    0.88
    ritional
    0.85
    ainer
    0.84
    rition
    0.83
    rien
    0.83
    ieth
    0.83
    iance
    0.82
    Activations Density 0.003%

    No Known Activations