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. 2-RES-JB
    6. 1251
    Prev
    Next
    INDEX
    Explanations

    photography-related terms and camera features

    oai_token-act-pair · gpt-3.5-turbo

    terms and concepts related to photography and camera features

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    taboola
    -0.73
    iless
    -0.72
    ONSORED
    -0.67
     Rodgers
    -0.67
     Levy
    -0.66
    ulla
    -0.66
     Brig
    -0.65
    owder
    -0.64
     Jenkins
    -0.63
    Closure
    -0.61
    POSITIVE LOGITS
    asonic
    0.87
    ometry
    0.83
     presets
    0.82
    stro
    0.79
    ometric
    0.77
     glide
    0.74
     codec
    0.74
     glyph
    0.74
     converter
    0.74
     horizont
    0.73
    Activations Density 0.360%

    No Known Activations