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

    Neuronpedia

    Jacobian LensNEW
    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. 7-RES-JB
    11. 1797
    Prev
    Next
    INDEX
    Explanations

    engine specifications related to power output

    oai_token-act-pair · gpt-3.5-turbo

    specific references to engine specifications and performance metrics

    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
     Shant
    -0.74
    idan
    -0.74
    leans
    -0.74
     Cheong
    -0.74
     fec
    -0.73
    gotten
    -0.73
    ouf
    -0.72
     Photographer
    -0.72
     Humanity
    -0.72
     Homeless
    -0.71
    POSITIVE LOGITS
     motors
    1.09
     turbo
    1.08
     engine
    1.07
    charged
    1.04
     horsepower
    1.03
     engines
    1.00
     diesel
    0.97
     torque
    0.96
     motor
    0.96
     brakes
    0.94
    Activations Density 0.123%

    No Known Activations