© 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. 10-RES_POST_32K-OAI
    11. 31370
    Prev
    Next
    INDEX
    Explanations

    mentions of individuals, particularly those with the name "Ignatyev" or similar variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res_post_32k-oai
    Configuration
    jbloom/GPT2-Small-OAI-v5-32k-resid-post-SAEs/v5_32k_layer_10.pt
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    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
    178
    +0.09
    0.4%
    96
    +0.09
    0.4%
    741
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    232
    +0.09
    0.01
    746
    +0.09
    0.01
    167
    +0.09
    0.00
    Negative Logits
    76561
    -0.78
    bian
    -0.70
    --------------------------------------------------------
    -0.69
    ktop
    -0.69
    lings
    -0.69
     Morph
    -0.65
    borg
    -0.63
     Shard
    -0.62
    scenes
    -0.60
     Typhoon
    -0.59
    POSITIVE LOGITS
    ition
    1.33
    oreAnd
    1.33
    acio
    1.25
    omin
    1.24
    orable
    1.17
    oring
    1.14
    ited
    1.11
    ores
    1.07
    ored
    1.06
    iting
    1.02
    Activations Density 0.050%

    No Known Activations