© 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. 20155
    Prev
    Next
    INDEX
    Explanations

    terms related to speed or acceleration

    oai_token-act-pair · gpt-3.5-turbo

    references to speed or velocity

    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
    oral
    -0.81
    roma
    -0.80
    eryl
    -0.79
    ortium
    -0.77
    arl
    -0.72
    riad
    -0.71
    bery
    -0.70
    pha
    -0.69
     Sark
    -0.68
    riel
    -0.67
    POSITIVE LOGITS
     speed
    1.16
     acceleration
    1.02
     speeds
    0.96
    wagon
    0.92
    speed
    0.90
    boat
    0.90
    iness
    0.89
    loader
    0.88
    boats
    0.87
    Speed
    0.87
    Activations Density 0.014%

    No Known Activations