Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 7-RES-JB
    6. 5454
    Prev
    Next
    INDEX
    Explanations

    phrases and words related to braking mechanisms

    oai_token-act-pair · gpt-3.5-turbo

    references to braking mechanisms and related components

    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
    swick
    -0.85
    anto
    -0.78
    itutional
    -0.77
    aldo
    -0.76
    guyen
    -0.73
    anta
    -0.72
    entious
    -0.71
    ertodd
    -0.71
    atana
    -0.71
    ISH
    -0.70
    POSITIVE LOGITS
     pedal
    1.22
     pedals
    1.06
     braking
    1.05
     brakes
    1.04
     pads
    0.98
     brake
    0.97
     booster
    0.82
     srf
    0.79
     horsepower
    0.77
     levers
    0.77
    Activations Density 0.050%

    No Known Activations