© 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. 13463
    Prev
    Next
    INDEX
    Explanations

    pronouns referring to a group or individuals in a group

    oai_token-act-pair · gpt-3.5-turbo

    pronouns related to collective actions or experiences

    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
     Flavoring
    -0.78
    itates
    -0.69
    pires
    -0.67
    uces
    -0.66
    Ô
    -0.64
    ifies
    -0.62
     inspires
    -0.61
     contributes
    -0.60
     facilitates
    -0.60
    iates
    -0.59
    POSITIVE LOGITS
     weren
    1.55
     were
    1.51
    were
    1.24
    're
    1.20
     knew
    1.15
    'd
    1.07
     hadn
    1.03
     didn
    1.02
     Were
    1.01
     reasoned
    0.99
    Activations Density 0.299%

    No Known Activations