© 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. 3-RES-JB
    11. 8311
    Prev
    Next
    INDEX
    Explanations

    generic descriptors like "whole" indicating evaluation and judgment

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "whole."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Blade
    -0.65
    inel
    -0.63
    KER
    -0.63
    minist
    -0.63
    Balt
    -0.61
     Cutter
    -0.61
    yip
    -0.60
    ministic
    -0.59
     Superintendent
    -0.58
    ulic
    -0.57
    POSITIVE LOGITS
    heartedly
    1.46
    hearted
    1.13
     gam
    0.87
     darn
    0.84
    whe
    0.70
     thing
    0.69
     freaking
    0.69
     Godd
    0.69
    oton
    0.66
     damn
    0.66
    Activations Density 0.025%

    No Known Activations