© 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. 2-RES-JB
    11. 9314
    Prev
    Next
    INDEX
    Explanations

    the word "ah" with variations in intensity

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific girl or woman named "Ah."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     insured
    -0.73
     fict
    -0.71
     paycheck
    -0.70
     fixation
    -0.70
     advoc
    -0.69
    é¾įå¥ij士
    -0.68
     totality
    -0.66
     gobl
    -0.66
     nomine
    -0.65
     ubiquitous
    -0.64
    POSITIVE LOGITS
    renheit
    1.38
    awk
    1.34
    awks
    1.20
    aha
    1.11
    olics
    1.09
    onda
    1.08
    ttp
    1.05
    oe
    1.02
    aban
    1.00
    ghan
    0.99
    Activations Density 0.012%

    No Known Activations