© 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. 1-RES-JB
    11. 24089
    Prev
    Next
    INDEX
    Explanations

    mention of omens and prophetic content

    oai_token-act-pair · gpt-3.5-turbo

    references to women and femininity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Fully
    -0.67
     Indies
    -0.66
     Battery
    -0.66
     Hampton
    -0.62
     screen
    -0.61
     Fiction
    -0.60
     Estimated
    -0.60
     4096
    -0.59
     Wish
    -0.59
     Residential
    -0.59
    POSITIVE LOGITS
    omen
    1.52
    opol
    0.95
    eday
    0.93
    stru
    0.92
    ocrats
    0.90
    oshenko
    0.90
    oso
    0.89
    nown
    0.88
    algia
    0.87
    DragonMagazine
    0.86
    Activations Density 0.007%

    No Known Activations