© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 8-RES-JB
    6. 20263
    Prev
    Next
    INDEX
    Explanations

    photographs with descriptions

    oai_token-act-pair · gpt-3.5-turbo

    references to photos or photographs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    urnal
    -0.71
    iazep
    -0.70
    adian
    -0.66
    wordpress
    -0.65
    yrinth
    -0.64
    uchs
    -0.62
    cffff
    -0.61
    omore
    -0.59
    astically
    -0.59
    anmar
    -0.58
    POSITIVE LOGITS
     Agency
    0.66
     toggle
    0.65
    Fran
    0.63
     IMAGES
    0.60
     Archive
    0.59
     Ltd
    0.57
     Tuls
    0.57
     Mehran
    0.56
     caption
    0.56
     Niet
    0.55
    Activations Density 0.021%

    No Known Activations