© 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. 9-RES-JB
    11. 15389
    Prev
    Next
    INDEX
    Explanations

    terms related to mechanical structures or systems

    oai_token-act-pair · gpt-3.5-turbo

    technical terms related to mechanisms and their functions

    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
    iaries
    -0.91
    apest
    -0.76
    iary
    -0.74
     Oval
    -0.72
    upon
    -0.69
    fig
    -0.68
    worthy
    -0.68
    lihood
    -0.66
    onga
    -0.66
     TAMADRA
    -0.66
    POSITIVE LOGITS
     mechanism
    0.91
    witz
    0.88
     Mechan
    0.87
     whereby
    0.87
     workings
    0.85
     mechanisms
    0.82
    ror
    0.80
     fracturing
    0.77
    ulic
    0.74
    utics
    0.72
    Activations Density 0.069%

    No Known Activations