© 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. 11454
    Prev
    Next
    INDEX
    Explanations

    pronouns followed by verbs indicating effort or intention

    oai_token-act-pair · gpt-3.5-turbo

    references to collective effort and group actions

    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
     Debor
    -0.75
     Amendments
    -0.70
    advertisement
    -0.69
    ç«
    -0.65
     Cosponsors
    -0.63
    emet
    -0.61
     Extensions
    -0.61
     Arri
    -0.59
    ction
    -0.56
    Render
    -0.56
    POSITIVE LOGITS
     possibly
    1.33
     feas
    1.13
     can
    1.13
     possible
    1.06
     practicable
    0.98
     Possible
    0.97
    can
    0.94
    Can
    0.92
    possibly
    0.88
     reasonably
    0.83
    Activations Density 0.081%

    No Known Activations