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. 7-RES-JB
    6. 16621
    Prev
    Next
    INDEX
    Explanations

    technical details related to specific vehicle models

    oai_token-act-pair · gpt-3.5-turbo

    references to specific car models and their features

    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
     Patreon
    -0.86
     fec
    -0.85
    tumblr
    -0.81
    iasis
    -0.81
    natureconservancy
    -0.79
     WikiLeaks
    -0.79
     spores
    -0.78
    pora
    -0.78
     parchment
    -0.77
    Sexual
    -0.76
    POSITIVE LOGITS
     chassis
    1.25
     racer
    1.22
     motors
    1.14
    Motor
    1.11
     Motor
    1.09
     motor
    1.08
     wheels
    1.07
     headlights
    1.04
     brakes
    1.04
     sedan
    1.04
    Activations Density 0.365%

    No Known Activations