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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 8-RES-JB
    11. 7602
    Prev
    Next
    INDEX
    Explanations

    programming code patterns related to file import and manipulation

    oai_token-act-pair · gpt-3.5-turbo

    punctuation marks, specifically periods

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     TAMADRA
    -1.01
     ampl
    -0.73
     Apprentice
    -0.68
     defe
    -0.68
     FN
    -0.66
     heresy
    -0.66
     Parish
    -0.64
     scoop
    -0.63
     calves
    -0.63
     electr
    -0.62
    POSITIVE LOGITS
    dll
    1.12
    github
    1.10
    json
    1.09
    google
    1.08
    std
    1.04
    local
    1.03
    html
    1.00
    ItemTracker
    1.00
    twitter
    0.96
    php
    0.96
    Activations Density 0.067%

    No Known Activations