© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 8-RES-JB
    11. 2691
    Prev
    Next
    INDEX
    Explanations

    mentions of horsepower values and car engine specifications

    oai_token-act-pair · gpt-3.5-turbo

    technical specifications and performance metrics of engines

    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
    Journal
    -0.90
     Gifts
    -0.85
     Identity
    -0.81
     Tumblr
    -0.81
     Cheong
    -0.81
     Cookie
    -0.79
     fec
    -0.77
     Feminist
    -0.77
     Sites
    -0.76
     Coinbase
    -0.76
    POSITIVE LOGITS
     torque
    1.41
     motors
    1.36
     braking
    1.29
     brakes
    1.28
     axle
    1.26
     horsepower
    1.25
     motor
    1.24
     piston
    1.21
     wheels
    1.19
     brake
    1.16
    Activations Density 0.297%

    No Known Activations