© 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. 14116
    Prev
    Next
    INDEX
    Explanations

    verbs that indicate a strong emotional or subjective perception

    oai_token-act-pair · gpt-3.5-turbo

    statements that express the quality or state of being

    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
    udeau
    -0.73
    ainers
    -0.69
    isions
    -0.68
    itches
    -0.67
     remarks
    -0.67
     Colomb
    -0.66
     Cards
    -0.64
     Guys
    -0.63
     Cheong
    -0.63
    rites
    -0.63
    POSITIVE LOGITS
     reminiscent
    1.02
     compatible
    0.99
     supposed
    0.98
    cedented
    0.97
     indistinguishable
    0.95
     designed
    0.95
     antit
    0.92
    nt
    0.92
     neither
    0.91
     incompatible
    0.90
    Activations Density 0.196%

    No Known Activations