© 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. 6233
    Prev
    Next
    INDEX
    Explanations

    phrases related to evaluations or judgments

    oai_token-act-pair · gpt-3.5-turbo

    words and phrases indicating a sense of fault or blame

    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
     division
    -0.75
     Gaul
    -0.74
     SAM
    -0.73
     divisions
    -0.70
     Scale
    -0.70
     Hud
    -0.69
     Rudd
    -0.68
     draw
    -0.68
     headlights
    -0.67
     Mole
    -0.67
    POSITIVE LOGITS
    responsible
    1.30
    extremely
    1.29
    very
    1.24
    usable
    1.19
    highly
    1.19
    expected
    1.16
    really
    1.16
    insured
    1.15
    reci
    1.14
    sufficient
    1.13
    Activations Density 0.095%

    No Known Activations