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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 6221
    Prev
    Next
    INDEX
    Explanations

    words or parts of words that include "ont" with numerical values following the pattern "ont <number>"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the term "ont" in various contexts

    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
     burned
    -0.69
     Heb
    -0.65
     bows
    -0.63
     folded
    -0.60
     above
    -0.60
     insol
    -0.60
     bow
    -0.60
     hammered
    -0.60
     Vice
    -0.59
     paid
    -0.59
    POSITIVE LOGITS
    ont
    4.56
    ONT
    2.07
    ond
    1.59
    onte
    1.56
    omm
    1.31
    ons
    1.29
    ount
    1.27
    onds
    1.24
    onto
    1.21
    ON
    1.10
    Activations Density 0.013%

    No Known Activations