© 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. 8645
    Prev
    Next
    INDEX
    Explanations

    terms related to city planning and development

    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
    459
    +0.11
    0.5%
    450
    +0.10
    0.4%
    561
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    659
    +0.11
    0.10
    232
    +0.10
    0.09
    284
    +0.09
    0.07
    Negative Logits
    warts
    -0.77
    weed
    -0.69
     destro
    -0.66
    andowski
    -0.65
    achev
    -0.65
    olicy
    -0.64
    pring
    -0.64
    ufact
    -0.64
    alties
    -0.63
    inav
    -0.61
    POSITIVE LOGITS
    rene
    0.60
    llah
    0.59
    utsche
    0.59
    reek
    0.58
    ciating
    0.56
     Nur
    0.56
    abeth
    0.56
    bia
    0.56
    Allah
    0.56
     Ala
    0.55
    Activations Density 1.075%

    No Known Activations