© 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. 3101
    Prev
    Next
    INDEX
    Explanations

    words related to details and observations in a narrative, especially related to different characters and their actions

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

    instances of individuals being skilled in multiple languages

    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
    assi
    -0.70
    Ô
    -0.68
    akable
    -0.66
    ĪĴ
    -0.66
    ikk
    -0.65
    rouse
    -0.65
    Clear
    -0.63
    uish
    -0.63
    iasm
    -0.62
    ngth
    -0.62
    POSITIVE LOGITS
     NEVER
    1.28
     actually
    1.27
     DID
    1.12
     DOES
    1.06
     hadn
    1.05
     REALLY
    1.04
     never
    1.03
     ONLY
    1.03
     wasn
    1.02
     NOT
    1.00
    Activations Density 0.804%

    No Known Activations