© 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. 6544
    Prev
    Next
    INDEX
    Explanations

    phrases expressing uncertainty or lack of commitment

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "really" indicating emphasis or qualification

    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
    tein
    -0.83
    ifully
    -0.70
    voy
    -0.68
    çļ
    -0.67
    moil
    -0.65
    thal
    -0.64
     nevertheless
    -0.63
    aciously
    -0.63
     nonetheless
    -0.62
    tex
    -0.62
    POSITIVE LOGITS
     anymore
    0.95
     bothered
    0.94
     bothering
    0.85
     bother
    0.84
    hin
    0.82
     cared
    0.79
     mattered
    0.75
     anywhere
    0.75
     appreciated
    0.72
     fit
    0.72
    Activations Density 0.037%

    No Known Activations