© 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. 24221
    Prev
    Next
    INDEX
    Explanations

    keywords related to mechanical parts, especially focusing on hinges

    oai_token-act-pair · gpt-3.5-turbo

    terms related to hinges and their functionality

    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
    ctica
    -0.88
    ioxide
    -0.79
    namese
    -0.78
    zanne
    -0.75
    aucas
    -0.73
    nel
    -0.73
    seys
    -0.72
    isance
    -0.72
     Marketable
    -0.71
    adan
    -0.71
    POSITIVE LOGITS
     hinge
    1.50
     hinges
    1.46
     closure
    0.78
     latch
    0.77
     lid
    0.77
    door
    0.76
    wheel
    0.76
     pend
    0.75
     clasp
    0.75
     gates
    0.74
    Activations Density 0.011%

    No Known Activations