© 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. 4-RES-JB
    11. 585
    Prev
    Next
    INDEX
    Explanations

    mentions of brake-related terms

    oai_token-act-pair · gpt-3.5-turbo

    terms related to braking and vehicle control

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

    No Comments

    Negative Logits
    anto
    -0.82
    ires
    -0.78
    guyen
    -0.78
    swick
    -0.76
    alg
    -0.72
    ourning
    -0.71
    entially
    -0.71
    ertain
    -0.70
    entious
    -0.68
    aldo
    -0.68
    POSITIVE LOGITS
     brakes
    1.21
     pedal
    1.16
     braking
    1.15
     brake
    1.05
     pedals
    1.02
     pads
    0.89
     booster
    0.85
     inhibitors
    0.83
     inhibitor
    0.79
     levers
    0.78
    Activations Density 0.010%

    No Known Activations