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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 8-RES-JB
    6. 21299
    Prev
    Next
    INDEX
    Explanations

    keywords related to motorcycle modifications and parts, particularly focusing on brakes and steering components

    oai_token-act-pair · gpt-3.5-turbo

    terms related to automotive braking systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Flavoring
    -1.01
     Homeless
    -0.84
    hemer
    -0.81
    DragonMagazine
    -0.79
    zynski
    -0.78
    azo
    -0.78
    icia
    -0.77
    natureconservancy
    -0.76
    女
    -0.72
    umblr
    -0.72
    POSITIVE LOGITS
     pedal
    1.22
     braking
    1.06
     brakes
    1.04
     pedals
    0.99
     brake
    0.99
     wheel
    0.99
     rotor
    0.98
     subsystem
    0.97
    charg
    0.96
     motor
    0.94
    Activations Density 0.173%

    No Known Activations