© 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. 3670
    Prev
    Next
    INDEX
    Explanations

    different types of textual markers or symbols such as brackets and quotes

    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
    250
    +0.13
    0.6%
    618
    +0.12
    0.6%
    218
    +0.12
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    407
    +0.13
    0.05
    286
    +0.12
    0.05
    346
    +0.12
    0.05
    Negative Logits
    ');
    -0.77
    legate
    -0.70
    washer
    -0.68
     indistinguishable
    -0.68
     hybrids
    -0.67
    emale
    -0.66
    VB
    -0.65
     equivalent
    -0.63
    .):
    -0.62
    luaj
    -0.62
    POSITIVE LOGITS
    theless
    0.75
    odcast
    0.69
     Ibid
    0.69
    iners
    0.68
    ablish
    0.68
    ccording
    0.68
     ..........
    0.65
    Phill
    0.64
    ewitness
    0.63
     Osw
    0.62
    Activations Density 0.384%

    No Known Activations