© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 0-RES-JB
    11. 18803
    Prev
    Next
    INDEX
    Explanations

    references to machinery parts related to engines

    oai_token-act-pair · gpt-3.5-turbo

    references to engines or engine-related topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     CES
    -0.76
     Kier
    -0.71
    Hay
    -0.68
     Bundy
    -0.67
     Holder
    -0.66
    label
    -0.66
     Sz
    -0.66
    anna
    -0.65
     taped
    -0.64
    Beck
    -0.63
    POSITIVE LOGITS
     engines
    3.93
     engine
    2.79
     Engine
    2.10
    engine
    1.88
    Engine
    1.74
     generators
    1.64
     motors
    1.61
     tyres
    1.53
     turbines
    1.44
     propulsion
    1.41
    Activations Density 0.024%

    No Known Activations