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. 22867
    Prev
    Next
    INDEX
    Explanations

    pronouns or proper nouns referring to individuals followed by an action or situation

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the pronoun "he" and related verbs indicating actions or events involving male characters

    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
    Score
    -0.73
    utical
    -0.71
     ILCS
    -0.69
    lead
    -0.66
    far
    -0.63
    cover
    -0.62
    iliate
    -0.59
     Exile
    -0.58
     Editors
    -0.57
     endorsements
    -0.56
    POSITIVE LOGITS
     noticed
    1.59
     encountered
    1.36
     spotted
    1.34
     realized
    1.31
     heard
    1.27
     realised
    1.26
     discovered
    1.24
     sensed
    1.23
     stumbled
    1.19
     overheard
    1.18
    Activations Density 0.234%

    No Known Activations