© 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. 0-RES-JB
    11. 12543
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to politics or news events

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the term "RO" which may refer to a specific organization or concept in the text

    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
     inspiration
    -0.61
     incarn
    -0.61
    ãĥ¼ãĥ³
    -0.59
    ergus
    -0.59
     McCorm
    -0.58
     episode
    -0.58
     Ammunition
    -0.58
     Sunderland
    -0.58
     Lect
    -0.58
     Hasan
    -0.57
    POSITIVE LOGITS
    RO
    4.51
     RO
    1.84
    ro
    1.67
    LO
    1.49
    ROM
    1.38
    Ro
    1.29
    RI
    1.25
    RON
    1.25
    RA
    1.23
    RE
    1.20
    Activations Density 0.012%

    No Known Activations