© 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. 18045
    Prev
    Next
    INDEX
    Explanations

    references to measurements, particularly those involving lengths or distances, such as 'inch' or 'ounce'

    oai_token-act-pair · gpt-3.5-turbo

    references to units of measurement, particularly inches and ounces

    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
    HCR
    -0.79
    ides
    -0.79
    peak
    -0.72
    ide
    -0.72
    hips
    -0.71
    ombs
    -0.68
    ported
    -0.68
     Aval
    -0.68
    occ
    -0.66
    mith
    -0.66
    POSITIVE LOGITS
     inch
    1.20
    catentry
    0.90
    wheel
    0.89
    naire
    0.82
     acre
    0.76
    worm
    0.75
     ounce
    0.74
    glass
    0.71
    vier
    0.69
    quart
    0.69
    Activations Density 0.008%

    No Known Activations