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. 7-RES-JB
    6. 20473
    Prev
    Next
    INDEX
    Explanations

    occurrences of specific movie titles

    oai_token-act-pair · gpt-3.5-turbo

    references to titles of films or literary works that begin with "The."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     patiently
    -0.71
     contributed
    -0.70
    lished
    -0.70
    omever
    -0.65
     endeav
    -0.64
    posted
    -0.64
    elsen
    -0.64
     authored
    -0.63
    perse
    -0.63
     behalf
    -0.63
    POSITIVE LOGITS
    atre
    1.17
    oret
    1.16
    orem
    1.09
    odor
    1.04
     Simpsons
    1.03
    resa
    1.02
    ories
    1.00
     Greatest
    1.00
    sis
    0.98
     Stranger
    0.95
    Activations Density 0.120%

    No Known Activations