© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 0-RES-JB
    11. 10490
    Prev
    Next
    INDEX
    Explanations

    keywords related to specific technical terms or names, particularly 'TS' and 'Raymond'

    oai_token-act-pair · gpt-3.5-turbo

    references to specific models and names related to automotive technology, particularly Toyota's TS series and individuals named Raymond

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     restitution
    -0.81
     Aqu
    -0.78
     Ox
    -0.74
    aqu
    -0.74
     aqu
    -0.73
    rav
    -0.73
     oxygen
    -0.71
    iol
    -0.70
     Oliv
    -0.69
    conom
    -0.67
    POSITIVE LOGITS
     TS
    3.65
     Raymond
    1.52
     ES
    1.12
     NAS
    1.08
     UCS
    1.00
     PTS
    0.97
     CSI
    0.95
     ts
    0.92
     FT
    0.84
     CF
    0.84
    Activations Density 0.026%

    No Known Activations