© 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. 20791
    Prev
    Next
    INDEX
    Explanations

    words related to employment changes and promotions

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the verb "to be" in various tense forms

    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
    PsyNetMessage
    -0.69
    odes
    -0.68
     Route
    -0.67
    itars
    -0.66
     Dreams
    -0.63
    ankind
    -0.63
    áµ
    -0.62
    development
    -0.62
     Doors
    -0.61
     anticipation
    -0.61
    POSITIVE LOGITS
     assassinated
    1.60
     sacked
    1.58
     indicted
    1.54
     ousted
    1.51
     acquitted
    1.48
     jailed
    1.43
     impe
    1.43
     expelled
    1.38
     fired
    1.38
     convicted
    1.37
    Activations Density 0.258%

    No Known Activations