© 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. 1-RES-JB
    11. 8691
    Prev
    Next
    INDEX
    Explanations

    references to software development tools or kits

    oai_token-act-pair · gpt-3.5-turbo

    references to various "Kit" products or packages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    arching
    -0.81
    cffffcc
    -0.79
    unct
    -0.76
     unions
    -0.69
    conv
    -0.67
     recru
    -0.66
     lobbying
    -0.63
    discrimination
    -0.63
    llor
    -0.63
     steroid
    -0.63
    POSITIVE LOGITS
    chens
    1.55
    Kit
    1.15
    chen
    1.14
    kat
    1.08
    Kat
    1.04
     Kats
    1.00
     Kit
    0.95
    amura
    0.94
    atsu
    0.90
    kit
    0.88
    Activations Density 0.005%

    No Known Activations