© 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. 15240
    Prev
    Next
    INDEX
    Explanations

    words related to pedals, such as 'pedal axle,' 'pedal chain,' and 'pedal technique.'

    oai_token-act-pair · gpt-3.5-turbo

    terms related to pedals and cycling mechanics

    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
    zona
    -0.84
    ews
    -0.77
    IFA
    -0.77
    cond
    -0.75
    reads
    -0.72
    abad
    -0.72
    aldo
    -0.70
    ioch
    -0.69
    uve
    -0.69
    ALD
    -0.68
    POSITIVE LOGITS
     pedal
    1.49
     pedals
    1.43
    bike
    0.87
    ãĥ¼ãĤ¯
    0.80
     paddle
    0.75
     slopes
    0.73
    ngth
    0.72
     motors
    0.70
     pads
    0.69
     bicycle
    0.68
    Activations Density 0.009%

    No Known Activations