© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 14132
    Prev
    Next
    INDEX
    Explanations

    references, notes, tags, comments related to specific topics within a text

    oai_token-act-pair · gpt-3.5-turbo

    references, comments, and tags in the document

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    agers
    -0.72
    ished
    -0.72
    boards
    -0.70
     mates
    -0.69
     faces
    -0.67
    ishment
    -0.66
    arding
    -0.66
    overs
    -0.65
    ALLY
    -0.64
    ously
    -0.63
    POSITIVE LOGITS
    ource
    1.16
    ystem
    1.12
    pring
    1.10
    poons
    1.09
    heet
    1.05
    uggest
    1.05
    cript
    1.02
    peed
    0.98
    cape
    0.97
    pace
    0.97
    Activations Density 0.175%

    No Known Activations