© 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. 24084
    Prev
    Next
    INDEX
    Explanations

    names of specific individuals

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific individuals, particularly those with the last name "Dawson" or "Walton."

    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
    eways
    -0.80
    juven
    -0.68
    reek
    -0.67
    _-
    -0.63
    tered
    -0.62
    enment
    -0.61
    ller
    -0.61
    esthetic
    -0.59
    ctions
    -0.58
    iltration
    -0.58
    POSITIVE LOGITS
     Dawson
    1.03
    ij士
    0.91
    ©¶æ¥µ
    0.85
    igans
    0.83
     Fury
    0.82
     Falls
    0.78
     metic
    0.76
     Springs
    0.74
     Skydragon
    0.74
     adolesc
    0.71
    Activations Density 0.004%

    No Known Activations