© 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. 7-RES-JB
    11. 17775
    Prev
    Next
    INDEX
    Explanations

    mentions of the University of California institutions

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the University of California system

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ultan
    -0.67
     bubbles
    -0.67
    paio
    -0.66
    odan
    -0.65
     curtains
    -0.62
    zb
    -0.61
     tur
    -0.61
     stains
    -0.60
     builder
    -0.58
    elist
    -0.57
    POSITIVE LOGITS
     Extension
    0.82
    uates
    0.77
     Libraries
    0.76
     Athletic
    0.75
     Robotics
    0.75
     Merrill
    0.73
     Hosp
    0.73
     Graduate
    0.71
     Applied
    0.71
     Laboratories
    0.70
    Activations Density 0.041%

    No Known Activations