© 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. 11-RES-JB
    11. 11228
    Prev
    Next
    INDEX
    Explanations

    proper nouns or names related to people or characters, especially those containing the substring 'Cra' or 'Kra'

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the names "Craven" and "Dra" along with related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    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
    worthiness
    -0.72
     Clover
    -0.71
    liest
    -0.69
    raint
    -0.68
     Claudia
    -0.63
     Newsp
    -0.62
     rounding
    -0.61
     Governors
    -0.59
     Tet
    -0.58
    gdala
    -0.57
    POSITIVE LOGITS
    igslist
    1.48
    pload
    1.27
    fters
    1.15
    ven
    1.10
    eger
    1.07
    fter
    1.05
    emer
    1.03
    igh
    0.98
    uth
    0.97
    iss
    0.96
    Activations Density 0.035%

    No Known Activations