© 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
    3. OpenAI · Sparse Autoencoder for GPT2-Small - v5 2024
    5. GPT2-Small
    7. Attention Out - 32k
    9. 3-ATT_32K-OAI
    11. 4018
    Prev
    Next
    INDEX
    Explanations

    phrases indicating intention or actions related to plans and strategies

    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
    497
    +0.14
    0.6%
    481
    +0.12
    0.6%
    25
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    142
    +0.14
    0.03
    104
    +0.12
    0.02
    328
    +0.09
    0.02
    Negative Logits
    Reviewer
    -0.70
    ãĤ´ãĥ³
    -0.69
     fodder
    -0.68
     corpus
    -0.65
     attracting
    -0.63
     numbering
    -0.63
     repe
    -0.62
     spirited
    -0.61
     revival
    -0.61
     stimulus
    -0.60
    POSITIVE LOGITS
    rone
    0.81
    ospace
    0.79
    plet
    0.78
    unia
    0.77
    iot
    0.76
    define
    0.76
    ctrl
    0.76
    iem
    0.76
    actionDate
    0.75
    chem
    0.74
    Activations Density 0.334%

    No Known Activations