© 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. 8-RES-JB
    11. 19341
    Prev
    Next
    INDEX
    Explanations

    mentions of specific locations and events

    oai_token-act-pair · gpt-3.5-turbo

    instances of the character "L" or related terms in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
     decomp
    -0.79
     JPEG
    -0.70
     scrim
    -0.66
     comb
    -0.65
     contempor
    -0.65
     photoc
    -0.63
     elim
    -0.63
     compost
    -0.63
     metaphor
    -0.62
     pyramid
    -0.61
    POSITIVE LOGITS
    s
    1.59
    ski
    1.15
    ship
    1.08
    sf
    1.07
    tal
    1.06
    sen
    1.02
    ses
    1.01
    ships
    1.00
    sg
    1.00
    sin
    0.99
    Activations Density 0.207%

    No Known Activations