© 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. 1-RES-JB
    11. 11170
    Prev
    Next
    INDEX
    Explanations

    words related to cylinders

    oai_token-act-pair · gpt-3.5-turbo

    references to types of cylinders, particularly in relation to oxygen and gas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    eur
    -0.74
    omen
    -0.73
    imates
    -0.70
    atz
    -0.70
    raviolet
    -0.68
    kers
    -0.68
    doms
    -0.68
    anamo
    -0.68
    orno
    -0.65
    olves
    -0.65
    POSITIVE LOGITS
     cylinder
    1.38
     cylinders
    1.38
     piston
    0.91
    ©¶æ¥µ
    0.84
     exting
    0.76
     refill
    0.73
    ttle
    0.72
     cyl
    0.72
     pedal
    0.71
    wheel
    0.71
    Activations Density 0.016%

    No Known Activations