© 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. 7800
    Prev
    Next
    INDEX
    Explanations

    phrases or symbols indicating code structure or variable definitions

    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
    178
    +0.12
    0.5%
    127
    +0.11
    0.5%
    409
    +0.11
    0.5%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    326
    +0.12
    0.01
    712
    +0.11
    0.01
    224
    +0.11
    0.01
    Negative Logits
    ADA
    -0.85
    cock
    -0.84
    packs
    -0.75
    weights
    -0.74
    blance
    -0.73
    ONES
    -0.72
    charg
    -0.70
    xus
    -0.69
    hift
    -0.66
    theless
    -0.65
    POSITIVE LOGITS
     guiActiveUn
    0.66
     Transcript
    0.65
    ãĥ¼ãĤ¯
    0.64
    ovic
    0.62
    ————————
    0.61
    olate
    0.61
    ollah
    0.60
     Cancer
    0.59
    cheon
    0.59
    ãĥ¼ãĥĨ
    0.59
    Activations Density 0.024%

    No Known Activations