© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 7-RES-JB
    11. 20909
    Prev
    Next
    INDEX
    Explanations

    terms related to the medical field, especially focusing on the suffix "-rol" and words related to health conditions

    oai_token-act-pair · gpt-3.5-turbo

    terms related to various roles or functions, particularly in a categorical or systematic context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    chal
    -0.76
    ELF
    -0.73
    hered
    -0.71
    κ
    -0.67
    REM
    -0.66
     Wem
    -0.65
    EMP
    -0.64
    Wan
    -0.64
    riad
    -0.64
    Glass
    -0.63
    POSITIVE LOGITS
    ogical
    1.27
    anguage
    1.24
    ounge
    1.15
    ateral
    1.07
    ibrary
    0.97
    ength
    0.96
    ution
    0.93
    oaded
    0.92
    wagen
    0.91
    s
    0.90
    Activations Density 0.064%

    No Known Activations