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. 0-RES-JB
    6. 23608
    Prev
    Next
    INDEX
    Explanations

    keywords related to the field of photography

    oai_token-act-pair · gpt-3.5-turbo

    references to photography in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ACK
    -0.68
    supp
    -0.65
    ATCH
    -0.63
    atech
    -0.63
    aker
    -0.62
     Invalid
    -0.62
    Pac
    -0.62
    anza
    -0.61
    Invalid
    -0.61
    Weak
    -0.61
    POSITIVE LOGITS
     photography
    3.69
     Photography
    2.68
     photographic
    1.95
     photograp
    1.94
     filmmaking
    1.72
     photographers
    1.68
     photographs
    1.62
    phot
    1.58
     photograph
    1.41
     photos
    1.40
    Activations Density 0.019%

    No Known Activations