© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 9-RES-JB
    6. 3271
    Prev
    Next
    INDEX
    Explanations

    References to photographs or images included in the text

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "Photograph."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     demol
    -0.66
     exerc
    -0.65
    rology
    -0.60
     Dominican
    -0.60
     retard
    -0.60
     neighboring
    -0.59
     submer
    -0.59
     leveling
    -0.59
     tant
    -0.58
    ŃĶ
    -0.58
    POSITIVE LOGITS
     Photograph
    1.06
    ograph
    0.86
    ically
    0.86
     ©
    0.85
     Courtesy
    0.84
    archive
    0.83
     caption
    0.80
    Phot
    0.79
    orial
    0.78
    ynthesis
    0.77
    Activations Density 0.029%

    No Known Activations