© 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. 4-RES-JB
    11. 19620
    Prev
    Next
    INDEX
    Explanations

    hyphenated words

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating a state of being or a significant change

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

    No Comments

    Negative Logits
    Ń·
    -0.91
     Cassidy
    -0.75
     Morales
    -0.72
     Richards
    -0.72
     Maher
    -0.72
     charms
    -0.71
    EStream
    -0.70
     wors
    -0.69
     Devil
    -0.68
     Krishna
    -0.68
    POSITIVE LOGITS
    sized
    1.13
    eyed
    1.10
    function
    1.06
    level
    1.04
    fledged
    1.02
    estate
    1.02
    bodied
    1.01
    hearted
    1.01
    exc
    1.00
    season
    0.98
    Activations Density 0.034%

    No Known Activations