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. 10233
    Prev
    Next
    INDEX
    Explanations

    reviews or opinions about movies

    oai_token-act-pair · gpt-3.5-turbo

    predictions about the future status or reception of films

    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
    tnc
    -0.77
    upper
    -0.63
     FSA
    -0.60
     sizing
    -0.59
    ebus
    -0.58
    iries
    -0.58
    arms
    -0.57
     denies
    -0.57
    Federal
    -0.56
    yne
    -0.56
    POSITIVE LOGITS
     cinematic
    1.00
     sequels
    0.97
     genre
    0.95
     sequel
    0.90
     parody
    0.90
    ilogy
    0.87
     starring
    0.83
     autobi
    0.82
    genre
    0.81
     cinem
    0.81
    Activations Density 1.101%

    No Known Activations