© 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. 9225
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "Eve" followed by a number

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "Eve" in various contexts

    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
    enegger
    -0.93
    Americans
    -0.85
    Downloadha
    -0.82
    aceutical
    -0.75
    umblr
    -0.73
    omo
    -0.71
    yout
    -0.71
    oho
    -0.68
    essee
    -0.68
    ificent
    -0.67
    POSITIVE LOGITS
    lyn
    1.24
    rette
    1.17
     Eve
    1.12
    lynn
    0.97
     Valkyrie
    0.95
    lla
    0.86
     Ens
    0.85
    ilon
    0.82
    lling
    0.73
    plan
    0.71
    Activations Density 0.010%

    No Known Activations