© 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. 3780
    Prev
    Next
    INDEX
    Explanations

    phrases that denote a sense of belonging or membership in a group

    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
    362
    +0.14
    0.6%
    134
    +0.10
    0.5%
    641
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    24
    +0.14
    0.06
    312
    +0.10
    0.05
    689
    +0.10
    0.05
    Negative Logits
     revolves
    -0.75
    gs
    -0.74
    ults
    -0.71
    hs
    -0.69
    hers
    -0.67
     resides
    -0.67
     replaces
    -0.66
     centers
    -0.66
    acters
    -0.64
    houses
    -0.64
    POSITIVE LOGITS
    aughtered
    0.65
    oÄŁan
    0.65
    ophile
    0.64
    apego
    0.63
    ulkan
    0.63
    dden
    0.62
     Arbor
    0.61
     Jury
    0.61
    angered
    0.61
     Enlight
    0.61
    Activations Density 0.191%

    No Known Activations