© 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. 12-RES-JB
    11. 3387
    Prev
    Next
    INDEX
    Explanations

    personal or professional titles and positions (e.g., staff writer, commentator, reporter)

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    references to journalists and their affiliations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aceae
    -0.82
    buster
    -0.75
    Ö¼
    -0.72
    atron
    -0.71
    alion
    -0.71
    onse
    -0.70
    forced
    -0.70
     undercut
    -0.68
    orus
    -0.68
    hess
    -0.66
    POSITIVE LOGITS
     Contribut
    1.34
     Featured
    1.28
     columnist
    1.26
     freelance
    1.18
     contributor
    1.17
     Editor
    1.16
     Journalism
    1.15
     Column
    1.15
     Opinion
    1.13
     Slate
    1.10
    Activations Density 0.234%

    No Known Activations