© 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. 16999
    Prev
    Next
    INDEX
    Explanations

    instances of the word "barely" with various degrees of strength

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "barely."

    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
     Parenthood
    -0.76
    onym
    -0.69
    rity
    -0.68
    uments
    -0.66
    sequence
    -0.65
    alm
    -0.64
     Bucket
    -0.64
    consumer
    -0.64
     Depot
    -0.63
     Purpose
    -0.63
    POSITIVE LOGITS
     scratched
    0.91
     scraping
    0.87
     glimps
    0.85
     survived
    0.83
     escaped
    0.81
     tolerated
    0.80
     scrape
    0.80
     percept
    0.79
     veiled
    0.79
     touched
    0.79
    Activations Density 0.031%

    No Known Activations