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. 11-RES-JB
    6. 7280
    Prev
    Next
    INDEX
    Explanations

    numerical data related to vehicle specifications

    oai_token-act-pair · gpt-3.5-turbo

    specifications and performance ratings of vehicles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tsy
    -0.78
     Poster
    -0.77
    Mask
    -0.75
     Patreon
    -0.70
    umbnail
    -0.69
     Username
    -0.68
     subscribing
    -0.67
    endants
    -0.67
    enta
    -0.66
     Mask
    -0.66
    POSITIVE LOGITS
     torque
    1.56
     braking
    1.46
     horsepower
    1.45
     cruising
    1.32
     acceleration
    1.24
     highway
    1.20
     Porsche
    1.17
     MPG
    1.17
     freeway
    1.16
     throttle
    1.15
    Activations Density 0.222%

    No Known Activations