© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. OpenAI · Sparse Autoencoder for GPT2-Small - v5 2024
    3. GPT2-Small
    4. Residual Post - 32k
    5. 10-RES_POST_32K-OAI
    6. 29358
    Prev
    Next
    INDEX
    Explanations

    instances of errors and warnings in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res_post_32k-oai
    Configuration
    jbloom/GPT2-Small-OAI-v5-32k-resid-post-SAEs/v5_32k_layer_10.pt
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    32,768
    Data Type
    torch.float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    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
    599
    +0.12
    0.5%
    371
    +0.10
    0.4%
    534
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    32
    +0.12
    0.01
    727
    +0.10
    0.01
    435
    +0.10
    0.01
    Negative Logits
    uay
    -0.79
    encers
    -0.75
     spaced
    -0.70
    uries
    -0.70
    imeters
    -0.68
    oshenko
    -0.68
    tein
    -0.67
    rums
    -0.66
    uesday
    -0.66
     shoulders
    -0.65
    POSITIVE LOGITS
    Language
    0.74
    !
    0.71
    !:
    0.69
     Language
    0.66
    External
    0.66
    Parent
    0.66
     Languages
    0.65
    Internal
    0.65
     Dram
    0.64
    Hom
    0.63
    Activations Density 0.067%

    No Known Activations