© 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. 6088
    Prev
    Next
    INDEX
    Explanations

    proper nouns that refer to works of literature, movies, or shows

    oai_token-act-pair · gpt-3.5-turbo

    possessive forms or references indicating ownership related to various subjects

    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
    oving
    -0.78
    force
    -0.76
    ACTED
    -0.72
    roup
    -0.71
    --+
    -0.70
    acts
    -0.70
    utz
    -0.70
    rit
    -0.69
    veland
    -0.66
    Experience
    -0.65
    POSITIVE LOGITS
     namesake
    1.38
     predecessor
    1.24
     creator
    1.22
     creators
    1.17
     narrator
    1.14
     protagonist
    1.13
     premise
    1.12
     subtitle
    1.11
     inception
    1.09
     genesis
    1.07
    Activations Density 0.203%

    No Known Activations