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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 0-RES-JB
    11. 4722
    Prev
    Next
    INDEX
    Explanations

    photographs

    oai_token-act-pair · gpt-3.5-turbo

    references to photographs and photography

    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
    erd
    -0.86
    Boost
    -0.68
     anyways
    -0.67
     Turbo
    -0.67
    ente
    -0.67
    _-
    -0.67
    core
    -0.66
    Weak
    -0.66
    tier
    -0.66
     backend
    -0.66
    POSITIVE LOGITS
     photographs
    3.43
     photograph
    3.21
     photographed
    2.51
     photograp
    2.39
     photographic
    2.28
     Photograph
    2.24
     photos
    2.23
     photography
    2.21
     pictures
    2.08
     photographers
    2.06
    Activations Density 0.013%

    No Known Activations