Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 8-RES-JB
    6. 1048
    Prev
    Next
    INDEX
    Explanations

    the word "Any"

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "Any ways," suggesting it looks for discussions about options or alternatives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rex
    -0.67
     epid
    -0.64
     Gomez
    -0.62
     Alps
    -0.62
     Halls
    -0.61
     Osc
    -0.59
    ously
    -0.57
    endas
    -0.57
    rez
    -0.56
     Oz
    -0.55
    POSITIVE LOGITS
    body
    1.53
    where
    1.40
    ways
    1.26
    how
    1.06
    THING
    1.04
    WHERE
    1.03
    time
    1.01
    WAYS
    0.91
    WAY
    0.90
    way
    0.86
    Activations Density 0.053%

    No Known Activations