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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 23764
    Prev
    Next
    INDEX
    Explanations

    mentions of product lineups

    oai_token-act-pair · gpt-3.5-turbo

    references to lineups in various contexts

    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
    legraph
    -0.75
    edu
    -0.68
     Cath
    -0.63
    ua
    -0.62
    verbs
    -0.61
    auld
    -0.60
    mit
    -0.60
    IGH
    -0.60
     landowners
    -0.59
    uay
    -0.59
    POSITIVE LOGITS
     lineup
    3.84
     roster
    1.83
     rosters
    1.39
     assortment
    1.23
     slate
    1.17
     portfolio
    1.15
     schedule
    1.15
     repertoire
    1.14
     matchup
    1.11
     line
    1.10
    Activations Density 0.012%

    No Known Activations