© 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. 21027
    Prev
    Next
    INDEX
    Explanations

    words related to technical difficulties or uncertainties

    oai_token-act-pair · gpt-3.5-turbo

    the presence of the word "te" in various contexts

    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
     Speedway
    -0.63
    INGTON
    -0.60
     federally
    -0.60
     overhead
    -0.58
     Woodward
    -0.57
     Atkinson
    -0.57
     Nationals
    -0.57
     broadly
    -0.56
     Wikimedia
    -0.55
     flaw
    -0.55
    POSITIVE LOGITS
    legraph
    1.54
    legram
    1.53
    eming
    1.41
    quila
    1.33
    asers
    1.29
    cn
    1.22
    chie
    1.15
    pee
    1.14
    achable
    1.13
    ases
    1.12
    Activations Density 0.019%

    No Known Activations