© 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 EvalsExportsAPI 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. 29031
    Prev
    Next
    INDEX
    Explanations

    identifiers and structured representations of data

    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
    139
    +0.10
    0.5%
    501
    +0.10
    0.5%
    430
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    232
    +0.10
    0.03
    137
    +0.10
    0.01
    326
    +0.10
    0.04
    Negative Logits
    sonian
    -0.76
     slic
    -0.72
    Reloaded
    -0.70
     supervisor
    -0.69
     cleaner
    -0.66
     exhib
    -0.65
     sten
    -0.65
     sched
    -0.64
    enburg
    -0.63
    orld
    -0.63
    POSITIVE LOGITS
     Rating
    1.03
    ellect
    0.99
     Requires
    0.96
     Points
    0.95
     Dexterity
    0.93
    Points
    0.88
     Equip
    0.86
     Agility
    0.85
    Strength
    0.77
    ngth
    0.74
    Activations Density 0.174%

    No Known Activations