© 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. 9-RES-JB
    11. 11197
    Prev
    Next
    INDEX
    Explanations

    Creative Commons (CC) license references, particularly focusing on CC license versions

    oai_token-act-pair · gpt-3.5-turbo

    instances of the 'CC' designation, likely related to copyright or creative commons licenses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Lans
    -0.70
    gery
    -0.69
    strument
    -0.66
    chest
    -0.65
    velt
    -0.65
    axy
    -0.64
    ãĤ¶
    -0.63
     Covenant
    -0.63
    metry
    -0.60
     Duck
    -0.60
    POSITIVE LOGITS
    entric
    1.05
    lean
    1.02
    ritical
    1.01
    redits
    0.92
    ombat
    0.92
    arthy
    0.91
    artney
    0.91
    olor
    0.91
    ategory
    0.90
    ording
    0.89
    Activations Density 0.053%

    No Known Activations