© 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
    2. OpenAI · Sparse Autoencoder for GPT2-Small - v5 2024
    3. GPT2-Small
    4. Attention Out - 32k
    5. 3-ATT_32K-OAI
    6. 4046
    Prev
    Next
    INDEX
    Explanations

    phrases related to assistance or facilitating action

    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
    542
    +0.12
    0.6%
    430
    +0.11
    0.5%
    637
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    504
    +0.12
    0.05
    307
    +0.11
    0.05
    276
    +0.11
    0.04
    Negative Logits
    oller
    -0.74
    aukee
    -0.72
     ultras
    -0.71
    vre
    -0.70
    ileged
    -0.68
    ggle
    -0.68
    OHN
    -0.67
    uum
    -0.67
    ihu
    -0.66
    ossibility
    -0.66
    POSITIVE LOGITS
    å¾
    0.70
    fund
    0.68
     testament
    0.67
     fiat
    0.63
     basis
    0.62
    saf
    0.59
    anon
    0.59
     precedent
    0.59
    kat
    0.58
     compounded
    0.57
    Activations Density 0.639%

    No Known Activations