© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 7816
    Prev
    Next
    INDEX
    Explanations

    phrases related to human body parts

    oai_token-act-pair · gpt-3.5-turbo

    terms related to arts and expressive forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     target
    -0.74
     Nom
    -0.73
     methyl
    -0.71
     scapego
    -0.68
     satur
    -0.67
     decl
    -0.66
     blackmail
    -0.66
     couch
    -0.65
     landslide
    -0.65
     statutory
    -0.65
    POSITIVE LOGITS
    arts
    4.92
    ART
    2.22
    art
    2.16
    arted
    2.07
    arters
    1.45
    arty
    1.39
    arter
    1.34
    arte
    1.26
    ards
    1.25
    ooters
    1.17
    Activations Density 0.009%

    No Known Activations