© 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. 8-RES_POST_32K-OAI
    11. 6398
    Prev
    Next
    INDEX
    Explanations

    URLs and numerical information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res_post_32k-oai
    Configuration
    jbloom/GPT2-Small-OAI-v5-32k-resid-post-SAEs/v5_32k_layer_8.pt
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    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
    745
    +0.11
    0.5%
    344
    +0.11
    0.5%
    331
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    238
    +0.11
    0.01
    462
    +0.11
    0.01
    331
    +0.11
    0.01
    Negative Logits
    yip
    -0.82
     psychiat
    -0.75
    oggles
    -0.73
    maxwell
    -0.69
     unbeliev
    -0.69
     millenn
    -0.68
     bombshell
    -0.68
    10000
    -0.67
     unden
    -0.66
    CLAIM
    -0.65
    POSITIVE LOGITS
     C
    0.75
     Tennis
    0.69
     Annotations
    0.69
     ESV
    0.68
     Unc
    0.66
    glers
    0.66
     Explicit
    0.66
    zel
    0.65
     âĨij
    0.64
     UTC
    0.64
    Activations Density 0.058%

    No Known Activations