© 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. 10-RES-JB
    11. 16290
    Prev
    Next
    INDEX
    Explanations

    instances of the sound "ah" that appear within words, especially when emphasized

    oai_token-act-pair · gpt-3.5-turbo

    instances of the sound "ah."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     secretaries
    -0.63
    chnology
    -0.61
     fixation
    -0.59
     suspic
    -0.58
     attention
    -0.58
     shorthand
    -0.57
     juices
    -0.56
     paycheck
    -0.56
     Daredevil
    -0.56
     closest
    -0.56
    POSITIVE LOGITS
    awk
    1.54
    awks
    1.45
    renheit
    1.37
    olics
    1.30
    aha
    1.17
    ouse
    1.11
    ttp
    1.11
    tml
    1.09
    ouston
    1.03
    olic
    1.03
    Activations Density 0.034%

    No Known Activations