© 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. 3990
    Prev
    Next
    INDEX
    Explanations

    references to customization and personalized elements

    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
    276
    +0.11
    0.5%
    80
    +0.10
    0.5%
    189
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    620
    +0.11
    0.03
    80
    +0.10
    0.03
    447
    +0.10
    0.04
    Negative Logits
    maxwell
    -0.86
    uble
    -0.81
    culosis
    -0.79
    Interstitial
    -0.74
     decline
    -0.73
    amate
    -0.73
    Ö¼
    -0.73
    alion
    -0.72
    anwhile
    -0.71
    hibition
    -0.71
    POSITIVE LOGITS
     customized
    0.76
     fitt
    0.76
     custom
    0.73
     compositions
    0.72
     arrangements
    0.68
     tailored
    0.68
     surfaces
    0.68
     attributes
    0.67
     settings
    0.67
     shapes
    0.67
    Activations Density 0.552%

    No Known Activations