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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    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. 11-RES-JB
    6. 15943
    Prev
    Next
    INDEX
    Explanations

    prepositions "in," "on," "to," and related words in phrases

    oai_token-act-pair · gpt-3.5-turbo

    prepositions and phrases indicating location or presence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    the phrase "in" followed by an article or determiner, typically signaling the beginning of a prepositional phrase or idiomatic expression.

    oai_token-act-pair · claude-3-5-sonnet-20240620Triggered by @danielepoterti
    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
     orally
    -0.60
    lection
    -0.57
     preceding
    -0.56
    lected
    -0.56
    By
    -0.55
    Skip
    -0.55
    itsch
    -0.53
    LAN
    -0.53
    by
    -0.52
     Helpful
    -0.52
    POSITIVE LOGITS
     danger
    1.16
     denial
    1.08
     trouble
    1.05
     awe
    1.04
    authent
    1.02
    escap
    1.00
    humane
    1.00
    bred
    0.98
    ching
    0.97
    offensive
    0.95
    Activations Density 0.110%

    No Known Activations