© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 4-RES-JB
    11. 7035
    Prev
    Next
    INDEX
    Explanations

    phrases related to photography

    oai_token-act-pair · gpt-3.5-turbo

    references to photography

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

    No Comments

    Negative Logits
    izen
    -0.69
    liner
    -0.65
    aneously
    -0.65
    este
    -0.64
     <+
    -0.64
    steen
    -0.64
    rir
    -0.63
    heimer
    -0.62
    clus
    -0.62
    ãĥİ
    -0.61
    POSITIVE LOGITS
     photography
    0.97
     studio
    0.80
     techniques
    0.80
     prowess
    0.78
     technique
    0.74
    ynthesis
    0.73
     proficiency
    0.73
     studios
    0.72
     Photography
    0.71
     microsc
    0.71
    Activations Density 0.026%

    No Known Activations