© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenAI · Sparse Autoencoder for GPT2-Small - v5 2024
    5. GPT2-Small
    7. Residual Post - 32k
    9. 10-RES_POST_32K-OAI
    11. 30135
    Prev
    Next
    INDEX
    Explanations

    instances of numerical values and structural elements in a document

    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
    602
    +0.11
    0.5%
    390
    +0.10
    0.5%
    373
    +0.10
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    688
    +0.11
    0.01
    150
    +0.10
    0.01
    373
    +0.10
    -0.02
    Negative Logits
     sovere
    -0.75
    tarian
    -0.74
    ÄŁ
    -0.73
    ministic
    -0.73
    76561
    -0.72
    ãĥķãĤ©
    -0.69
    ãĥĺ
    -0.69
     perspect
    -0.67
    gans
    -0.66
    mas
    -0.63
    POSITIVE LOGITS
     LO
    0.87
     Average
    0.70
    orio
    0.64
     Strip
    0.63
     OVER
    0.61
     Module
    0.60
     ART
    0.59
    unct
    0.59
     Grad
    0.59
     Median
    0.58
    Activations Density 0.113%

    No Known Activations