© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 1176
    Prev
    Next
    INDEX
    Explanations

    the word "Any" at the beginning of a sentence

    oai_token-act-pair · gpt-3.5-turbo

    the word "Any" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Kamp
    -0.58
    alus
    -0.58
    azon
    -0.58
     theirs
    -0.56
     Bakr
    -0.56
     Annex
    -0.56
    ariat
    -0.55
    orial
    -0.55
    iverse
    -0.54
     Originally
    -0.54
    POSITIVE LOGITS
    body
    1.62
    where
    1.47
    ways
    1.43
    how
    1.42
    time
    1.39
    who
    1.12
    THING
    1.12
    WHERE
    1.10
    WAYS
    1.06
    WAY
    1.04
    Activations Density 0.053%

    No Known Activations