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. 6-RES-JB
    6. 6546
    Prev
    Next
    INDEX
    Explanations

    references to photographers with positive descriptions and actions related to photography

    oai_token-act-pair · gpt-3.5-turbo

    references to photographers and photography

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    steen
    -0.80
    ricular
    -0.78
    hurst
    -0.76
    emonic
    -0.72
    rase
    -0.71
    auri
    -0.70
    brace
    -0.68
    ulhu
    -0.68
    inence
    -0.68
    croft
    -0.68
    POSITIVE LOGITS
     Photographer
    1.14
     photographers
    1.13
     photographer
    1.05
     photography
    0.98
     galleries
    0.96
     photograp
    0.93
     Nikon
    0.93
     gallery
    0.92
    ynthesis
    0.92
    photos
    0.91
    Activations Density 0.022%

    No Known Activations