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

    Neuronpedia

    APICircuit 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. 15536
    Prev
    Next
    INDEX
    Explanations

    phrases related to movies and entertainment sequels or continuations

    oai_token-act-pair · gpt-3.5-turbo

    elements related to television series, particularly those that feature new or recurring storylines and 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
    à¼
    -0.94
    EPA
    -0.85
    HCR
    -0.84
    alde
    -0.82
    ï
    -0.80
    Figure
    -0.79
    Federal
    -0.79
    ogy
    -0.78
    fax
    -0.77
    externalActionCode
    -0.76
    POSITIVE LOGITS
     sequels
    1.29
     flashbacks
    1.25
     storylines
    1.19
     villains
    1.12
     characters
    1.08
     vampires
    1.06
     supernatural
    1.03
     superheroes
    1.02
     mutants
    1.02
     collaborations
    1.00
    Activations Density 0.458%

    No Known Activations