© 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. 4-RES-JB
    11. 6765
    Prev
    Next
    INDEX
    Explanations

    references to the concept of "repeal" in a document

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "repeal."

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

    No Comments

    Negative Logits
     fullest
    -0.69
    semb
    -0.66
     incorpor
    -0.66
     warr
    -0.64
    TeX
    -0.64
     Ange
    -0.63
     bios
    -0.62
     Topic
    -0.62
     concess
    -0.62
     Seym
    -0.61
    POSITIVE LOGITS
    vation
    0.96
    phal
    0.87
    pha
    0.86
    aries
    0.85
    tering
    0.84
    itual
    0.83
    rals
    0.83
    ances
    0.82
    ming
    0.82
    chemy
    0.79
    Activations Density 0.021%

    No Known Activations