© 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. 21062
    Prev
    Next
    INDEX
    Explanations

    mentions of legal or controversial matters

    oai_token-act-pair · gpt-3.5-turbo

    punctuation and specific numerical 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
    ensity
    -0.69
    iphate
    -0.69
    ouble
    -0.67
    mble
    -0.67
    Explore
    -0.67
    "}],"
    -0.66
    rossover
    -0.66
    rawl
    -0.65
    icult
    -0.65
    omever
    -0.64
    POSITIVE LOGITS
     prompting
    1.30
     thereby
    1.29
     causing
    1.20
     triggering
    1.16
     resulting
    1.15
     sparking
    1.13
     forcing
    1.12
     thus
    1.06
     ruining
    1.05
     depri
    1.05
    Activations Density 0.369%

    No Known Activations