© 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. 3-RES-JB
    11. 3111
    Prev
    Next
    INDEX
    Explanations

    prepositions and phrases indicating position or direction

    oai_token-act-pair · gpt-3.5-turbo

    prepositions and phrases indicating relationships or connections in context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Pwr
    -0.39
     :=
    -0.34
    idav
    -0.33
     WATCHED
    -0.32
    Shield
    -0.31
    wcs
    -0.31
    catentry
    -0.31
    CNN
    -0.31
    SourceFile
    -0.30
    iltr
    -0.30
    POSITIVE LOGITS
    bidden
    0.40
    gery
    0.36
     eternity
    0.34
     afar
    0.33
     any
    0.32
     the
    0.31
     fruition
    0.31
    geries
    0.31
     those
    0.30
     behalf
    0.30
    Activations Density 1.736%

    No Known Activations