© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 3456
    Prev
    Next
    INDEX
    Explanations

    occurrences of the phrase "it is" in various contexts

    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
    218
    +0.15
    0.7%
    94
    +0.11
    0.5%
    667
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    613
    +0.15
    0.03
    8
    +0.11
    0.03
    630
    +0.10
    0.03
    Negative Logits
    ÄŁ
    -0.85
    idium
    -0.80
    atem
    -0.72
    rays
    -0.72
    eln
    -0.72
    letico
    -0.70
    gue
    -0.69
    atis
    -0.69
    rup
    -0.68
    inge
    -0.67
    POSITIVE LOGITS
     addictive
    0.64
     OCD
    0.63
     funny
    0.63
     Skinner
    0.62
     depressing
    0.60
     hilarious
    0.60
    Honest
    0.60
     Happiness
    0.59
     Locked
    0.58
     Solitaire
    0.58
    Activations Density 0.359%

    No Known Activations