© 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. 4627
    Prev
    Next
    INDEX
    Explanations

    text cues related to making choices or selections in instructions or descriptions

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

    variations of the word "choosing" and its context

    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
     mileage
    -0.61
     inaccur
    -0.59
    ALLY
    -0.58
     crate
    -0.58
    wear
    -0.54
     innocence
    -0.54
     frustrations
    -0.54
    nings
    -0.53
     foul
    -0.53
     Bethlehem
    -0.52
    POSITIVE LOGITS
    osing
    1.41
    pper
    1.34
    ices
    1.31
    ppy
    1.22
    ppers
    1.22
    oser
    1.20
    ppa
    1.15
    irs
    1.14
    oses
    1.10
    osen
    1.09
    Activations Density 0.028%

    No Known Activations