© 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. 14254
    Prev
    Next
    INDEX
    Explanations

    terms related to scientific research, studies, and publications

    oai_token-act-pair · gpt-3.5-turbo

    references to published scientific studies and research findings

    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
     caster
    -0.74
    Lago
    -0.70
     broom
    -0.70
    typ
    -0.69
    cott
    -0.68
    tones
    -0.67
    caster
    -0.66
    arer
    -0.66
    dos
    -0.62
    service
    -0.61
    POSITIVE LOGITS
    Explore
    0.95
    ournals
    0.93
     published
    0.91
     Neuroscience
    0.91
     neuroscience
    0.91
     doctoral
    0.91
     authors
    0.90
     findings
    0.90
    doi
    0.90
     Proceedings
    0.90
    Activations Density 0.262%

    No Known Activations