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. 3-RES-JB
    6. 7370
    Prev
    Next
    INDEX
    Explanations

    terms related to photography and image processing

    oai_token-act-pair · gpt-3.5-turbo

    references to photographic technology and related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uyomi
    -0.78
    Interstitial
    -0.76
    resso
    -0.73
    uliffe
    -0.73
     Civic
    -0.72
    tta
    -0.72
    GROUND
    -0.71
    oldemort
    -0.69
     Rutherford
    -0.68
    awaru
    -0.68
    POSITIVE LOGITS
     phot
    1.24
    ographs
    1.16
     Phot
    1.08
    oshop
    1.07
    ograph
    0.96
    ocard
    0.93
    ographed
    0.90
    Phot
    0.90
    ographers
    0.88
    ograp
    0.88
    Activations Density 0.011%

    No Known Activations