© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 9122
    Prev
    Next
    INDEX
    Explanations

    references to negative characteristics or descriptors

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Neuron Alignment
    Index
    Value
    % of L₁
    526
    +0.13
    0.6%
    216
    +0.12
    0.6%
    726
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    147
    +0.13
    0.02
    406
    +0.12
    0.02
    170
    +0.11
    0.02
    Negative Logits
    chy
    -0.78
    pton
    -0.77
    hov
    -0.72
    cci
    -0.67
    plets
    -0.66
    pheus
    -0.65
    gee
    -0.65
    ettings
    -0.64
    ptive
    -0.64
    plet
    -0.63
    POSITIVE LOGITS
    rophe
    1.29
    rophic
    1.10
    efully
    1.01
    eful
    1.01
    roph
    1.00
    rike
    0.97
    ruct
    0.95
    rians
    0.92
    rian
    0.92
    eele
    0.92
    Activations Density 0.055%

    No Known Activations