© 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 EvalsExportsinterp-engineNEWAPI 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. 8000
    Prev
    Next
    INDEX
    Explanations

    references to specific numerical identifiers or values

    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
    223
    +0.12
    0.5%
    373
    +0.12
    0.5%
    598
    +0.10
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.12
    0.02
    316
    +0.12
    0.01
    11
    +0.10
    0.01
    Negative Logits
     chin
    -0.72
    ania
    -0.60
    tered
    -0.60
    overs
    -0.60
    pora
    -0.59
     mosa
    -0.58
     Ange
    -0.58
    lict
    -0.58
     advoc
    -0.58
     clen
    -0.58
    POSITIVE LOGITS
    st
    1.12
    essor
    0.86
    041
    0.84
    0
    0.84
    vier
    0.82
    BUG
    0.82
    onsense
    0.81
    043
    0.80
    09
    0.78
    08
    0.77
    Activations Density 0.058%

    No Known Activations