© 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 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. 9-RES-JB
    11. 2305
    Prev
    Next
    INDEX
    Explanations

    terms related to technical computer systems, such as software and hardware elements

    oai_token-act-pair · gpt-3.5-turbo

    references to specific products or technologies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Åį
    -0.60
     ÂŃ
    -0.59
    ÂŃ
    -0.56
    Äĵ
    -0.52
     lawmakers
    -0.51
    umerable
    -0.51
     congressional
    -0.50
    ocamp
    -0.50
    elong
    -0.50
    Ö
    -0.48
    POSITIVE LOGITS
     dont
    0.63
     etc
    0.62
     ;)
    0.61
     tho
    0.60
     eg
    0.58
     wik
    0.55
     physic
    0.54
     ie
    0.54
    :-
    0.54
     Extras
    0.53
    Activations Density 1.800%

    No Known Activations