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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 7444
    Prev
    Next
    INDEX
    Explanations

    terms related to interruptions and disruptions

    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
    271
    +0.14
    0.6%
    361
    +0.13
    0.6%
    275
    +0.13
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    271
    +0.14
    0.03
    288
    +0.13
    0.04
    195
    +0.13
    0.01
    Negative Logits
    phans
    -0.71
    uncle
    -0.68
    angs
    -0.67
    eah
    -0.67
    uct
    -0.65
    illac
    -0.64
    bold
    -0.64
    rie
    -0.63
    hl
    -0.63
    silver
    -0.63
    POSITIVE LOGITS
     disrupted
    0.89
    ions
    0.87
     disruptions
    0.77
     curfew
    0.75
    alore
    0.74
     bowel
    0.71
     interruption
    0.70
    ĸļ
    0.69
    ante
    0.69
    urations
    0.69
    Activations Density 0.203%

    No Known Activations