© 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. 29202
    Prev
    Next
    INDEX
    Explanations

    terms related to available choices and alternatives

    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
    427
    +0.12
    0.5%
    121
    +0.12
    0.5%
    763
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    679
    +0.12
    0.11
    724
    +0.12
    0.10
    247
    +0.10
    0.07
    Negative Logits
    mble
    -0.70
    ustomed
    -0.68
    gian
    -0.65
     propensity
    -0.65
    ORN
    -0.65
    arde
    -0.64
    algia
    -0.63
     Thumbnails
    -0.63
    phies
    -0.63
     brunt
    -0.59
    POSITIVE LOGITS
     alternatives
    1.13
     options
    1.11
     available
    1.06
     alternative
    1.02
     Alternative
    0.99
     Altern
    0.97
    Option
    0.96
     Option
    0.96
     option
    0.96
     viable
    0.93
    Activations Density 1.233%

    No Known Activations