© 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. 23565
    Prev
    Next
    INDEX
    Explanations

    distances in kilometers expressed in numerical form

    oai_token-act-pair · gpt-3.5-turbo
    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
    gotten
    -0.72
    comes
    -0.71
     Semin
    -0.66
    inse
    -0.64
     Stri
    -0.61
     Wong
    -0.60
     Palace
    -0.60
    FORE
    -0.59
     bearer
    -0.59
    rors
    -0.59
    POSITIVE LOGITS
     km
    1.20
    km
    1.02
     kilometers
    0.99
     kilometres
    0.96
     lapt
    0.92
    iking
    0.79
    SPA
    0.77
     kilomet
    0.74
     miles
    0.72
     mile
    0.71
    Activations Density 0.009%

    No Known Activations