© 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
    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. 23483
    Prev
    Next
    INDEX
    Explanations

    instances of the word "any" followed by various context-dependent words or phrases

    oai_token-act-pair · gpt-3.5-turbo

    phrases that express the concept of "any" or "any more" in various contexts

    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
    Reviewed
    -0.59
    azon
    -0.58
     Converted
    -0.57
     Comes
    -0.55
    arb
    -0.54
     pend
    -0.54
     Perspect
    -0.54
    urst
    -0.53
    atem
    -0.52
     Esports
    -0.51
    POSITIVE LOGITS
    how
    1.41
    place
    1.12
    WHERE
    1.11
     longer
    1.05
    more
    1.00
    MORE
    0.96
    where
    0.95
    etheless
    0.92
    thin
    0.92
     wiser
    0.91
    Activations Density 0.048%

    No Known Activations