© 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. Residual Post - 32k
    9. 8-RES_POST_32K-OAI
    11. 5974
    Prev
    Next
    INDEX
    Explanations

    phrases indicating familiarity or unfamiliarity with a subject or topic

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_post_32k-oai
    Configuration
    jbloom/GPT2-Small-OAI-v5-32k-resid-post-SAEs/v5_32k_layer_8.pt
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    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
    91
    +0.10
    0.5%
    669
    +0.09
    0.4%
    572
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    669
    +0.10
    0.05
    608
    +0.09
    0.06
    641
    +0.09
    0.05
    Negative Logits
    ratulations
    -0.85
    earchers
    -0.82
     teasp
    -0.81
    erity
    -0.79
    appointed
    -0.76
    rings
    -0.75
    enaries
    -0.74
    enary
    -0.71
    \/\/
    -0.71
    eca
    -0.69
    POSITIVE LOGITS
     how
    0.84
     what
    0.75
     ropes
    0.75
     classical
    0.73
     basics
    0.73
     English
    0.73
     geography
    0.72
     firsthand
    0.72
     languages
    0.69
     navigating
    0.69
    Activations Density 0.307%

    No Known Activations