© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 2178
    Prev
    Next
    INDEX
    Explanations

    words related to languages and fluency

    oai_token-act-pair · gpt-3.5-turbo

    terms related to language and linguistics

    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
    kus
    -0.95
    romeda
    -0.91
    roxy
    -0.87
    oppable
    -0.86
    nuts
    -0.85
    ecake
    -0.77
    rieved
    -0.77
    nut
    -0.74
    apego
    -0.74
    OHN
    -0.73
    POSITIVE LOGITS
     spoken
    1.19
     learners
    1.15
     proficiency
    1.14
     barrier
    1.11
     lear
    1.07
     interpreter
    1.06
     flu
    0.95
     immersion
    0.94
     translation
    0.94
     Lear
    0.91
    Activations Density 0.067%

    No Known Activations