© 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. 8-RES-JB
    11. 12937
    Prev
    Next
    INDEX
    Explanations

    names of persons or characters

    oai_token-act-pair · gpt-3.5-turbo

    important names or nouns relevant to specific entities or activities

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    ilater
    -0.70
     nationally
    -0.59
     undermin
    -0.59
     predec
    -0.58
     arrang
    -0.58
    ãĥ¼ãĥĨ
    -0.58
     Surviv
    -0.56
    LIST
    -0.55
     unaff
    -0.55
    PDATE
    -0.55
    POSITIVE LOGITS
    osaurus
    0.84
     Profile
    0.83
     AFB
    0.78
    aceae
    0.73
    opsis
    0.73
     Brothers
    0.67
    nikov
    0.65
    ia
    0.65
     Says
    0.64
     County
    0.64
    Activations Density 0.385%

    No Known Activations