© 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. 5202
    Prev
    Next
    INDEX
    Explanations

    instances of the word "triple" related to numerical values or scores

    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
    651
    +0.13
    0.6%
    472
    +0.12
    0.5%
    122
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    651
    +0.13
    0.04
    81
    +0.12
    0.03
    699
    +0.10
    0.02
    Negative Logits
    sbm
    -0.70
    Downloadha
    -0.69
    istry
    -0.68
    latest
    -0.66
    ears
    -0.65
    hammad
    -0.65
    papers
    -0.65
    earing
    -0.64
    ega
    -0.64
    Dialogue
    -0.63
    POSITIVE LOGITS
    plet
    1.03
    plets
    1.00
    ty
    0.91
    ts
    0.88
    header
    0.84
    toe
    0.81
    leans
    0.78
    teen
    0.78
    reme
    0.76
    ple
    0.76
    Activations Density 0.102%

    No Known Activations