© 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. 0-RES-JB
    11. 12884
    Prev
    Next
    INDEX
    Explanations

    terms related to braking systems on vehicles

    oai_token-act-pair · gpt-3.5-turbo

    terms associated with braking systems and their components

    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
    \-
    -0.79
    Vill
    -0.73
    rn
    -0.72
     Tribal
    -0.69
     Oz
    -0.69
     Legion
    -0.68
    alla
    -0.68
    vg
    -0.67
     Horde
    -0.65
    AMI
    -0.65
    POSITIVE LOGITS
     brakes
    4.22
     brake
    3.59
     braking
    2.76
     pedals
    1.72
    bra
    1.55
     accelerator
    1.55
     pedal
    1.54
     throttle
    1.51
     tyres
    1.39
     levers
    1.29
    Activations Density 0.022%

    No Known Activations