© 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. 30774
    Prev
    Next
    INDEX
    Explanations

    references to concepts involving exploration or expansion

    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
    294
    +0.10
    0.5%
    575
    +0.09
    0.4%
    358
    +0.09
    0.4%
    Correlated Neurons
    Index
    P. Corr.
    Cos Sim.
    208
    +0.10
    0.01
    120
    +0.09
    0.01
    503
    +0.09
    0.01
    Negative Logits
     Crom
    -0.67
     Hook
    -0.66
     Carnival
    -0.65
     Luck
    -0.63
     FDR
    -0.60
     Cock
    -0.60
     Pebble
    -0.60
     Admir
    -0.59
    GROUND
    -0.58
     Tinker
    -0.58
    POSITIVE LOGITS
    ropri
    1.50
    orters
    1.46
    orter
    1.45
    anse
    1.36
    ository
    1.30
    iring
    1.28
    resso
    1.27
    onents
    1.26
    atri
    1.23
    iry
    1.23
    Activations Density 0.044%

    No Known Activations