© 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. 0-RES-JB
    11. 20187
    Prev
    Next
    INDEX
    Explanations

    instances of the word "Bel" associated with people's names

    oai_token-act-pair · gpt-3.5-turbo

    the presence of variations of the word "believe"

    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
     Gallery
    -0.67
     adjourn
    -0.67
     delinquent
    -0.65
     reversed
    -0.64
     compounded
    -0.63
     interrupted
    -0.62
     sorted
    -0.62
     deferred
    -0.62
     snapping
    -0.61
     Directions
    -0.61
    POSITIVE LOGITS
    bel
    4.40
    Bel
    1.75
     BEL
    1.71
     Bel
    1.38
    belt
    1.38
    bell
    1.36
    bek
    1.14
    bes
    1.13
    faith
    1.12
    bos
    1.12
    Activations Density 0.013%

    No Known Activations