© 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. 10-RES_POST_32K-OAI
    11. 29990
    Prev
    Next
    INDEX
    Explanations

    references to geographical locations and associated entities like courts and government departments

    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
    36
    +0.12
    0.6%
    414
    +0.10
    0.5%
    314
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    752
    +0.12
    0.10
    288
    +0.10
    0.09
    152
    +0.09
    0.07
    Negative Logits
    cases
    -0.88
    ernels
    -0.86
    sites
    -0.85
    aneers
    -0.83
    Americans
    -0.83
    andals
    -0.82
    units
    -0.82
    casts
    -0.81
    idents
    -0.80
    rencies
    -0.80
    POSITIVE LOGITS
     aide
    0.85
     staffer
    0.82
     source
    0.80
     delegation
    0.80
     colleague
    0.79
    inav
    0.78
     spokeswoman
    0.78
     official
    0.78
     surrogate
    0.77
     courtroom
    0.76
    Activations Density 1.061%

    No Known Activations