© 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. 3-RES-JB
    11. 1727
    Prev
    Next
    INDEX
    Explanations

    phrases related to automotive horsepower

    oai_token-act-pair · gpt-3.5-turbo

    terms related to engine performance and specifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    gotten
    -0.76
    umn
    -0.76
     Costume
    -0.73
    estine
    -0.73
    idan
    -0.71
     Atlantis
    -0.71
     Lonely
    -0.71
    ril
    -0.70
     Cron
    -0.70
    avis
    -0.69
    POSITIVE LOGITS
     horsepower
    1.14
     torque
    1.01
     pumps
    0.98
     pedals
    0.94
     piston
    0.94
     takeoff
    0.94
     displacement
    0.93
     capacities
    0.90
     braking
    0.89
     pedal
    0.88
    Activations Density 0.028%

    No Known Activations