© 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 EvalsExportsinterp-engineNEWAPI 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. 0-RES-JB
    11. 15175
    Prev
    Next
    INDEX
    Explanations

    terms related to a condition or topic labeled as "SS"

    oai_token-act-pair · gpt-3.5-turbo

    repeated mentions of a specific abbreviation or term, likely related to a subject matter or field

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    azeera
    -0.73
    athon
    -0.66
     fract
    -0.66
    ophon
    -0.63
     Foley
    -0.63
     Lima
    -0.63
     âĶ
    -0.62
     clam
    -0.61
    obe
    -0.61
    lah
    -0.61
    POSITIVE LOGITS
     SS
    3.90
    SS
    2.31
     ss
    1.45
     DS
    1.33
     SR
    1.29
     FS
    1.25
     SB
    1.22
     NS
    1.22
     RS
    1.21
     DH
    1.20
    Activations Density 0.022%

    No Known Activations