© 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. 30958
    Prev
    Next
    INDEX
    Explanations

    mathematical functions and programming operations related to data processing and analysis

    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
    760
    +0.13
    0.6%
    158
    +0.13
    0.6%
    223
    +0.13
    0.6%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.13
    0.11
    158
    +0.13
    0.10
    678
    +0.13
    0.08
    Negative Logits
     Mehran
    -0.76
    catentry
    -0.67
     munitions
    -0.64
    ModLoader
    -0.63
     invention
    -0.62
    BuyableInstoreAndOnline
    -0.62
    lishing
    -0.61
     antioxid
    -0.60
    idelines
    -0.59
     manoeuv
    -0.59
    POSITIVE LOGITS
     <-
    1.14
     [|
    0.96
     expr
    0.91
     [(
    0.89
    Nat
    0.85
    Maybe
    0.84
     ::
    0.83
    lift
    0.83
     Nothing
    0.83
    IOR
    0.83
    Activations Density 0.806%

    No Known Activations