© 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. 9-RES-JB
    11. 4192
    Prev
    Next
    INDEX
    Explanations

    names of characters or entities in a narrative context

    oai_token-act-pair · gpt-3.5-turbo

    the presence of specific characters or names from a fantasy universe

    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
     Univ
    -0.86
     ballpark
    -0.83
     PCR
    -0.83
     confir
    -0.80
     newsletters
    -0.78
     wastewater
    -0.75
     weekday
    -0.75
     enrichment
    -0.74
     CMS
    -0.74
     PRESS
    -0.72
    POSITIVE LOGITS
    beard
    1.14
    ilda
    1.13
    osuke
    1.12
    ilyn
    1.10
    uko
    1.10
    ako
    1.10
    akuya
    1.07
    abeth
    1.07
    uka
    1.05
    iko
    1.05
    Activations Density 0.340%

    No Known Activations