Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 21647
    Prev
    Next
    INDEX
    Explanations

    measurements of length

    oai_token-act-pair · gpt-3.5-turbo

    measurements of length or height in inches

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

    No Comments

    Negative Logits
    actionDate
    -0.95
    eer
    -0.82
    eem
    -0.72
    odor
    -0.71
    analysis
    -0.71
    tenance
    -0.70
    ggies
    -0.70
    infeld
    -0.68
     Mothers
    -0.68
    akespe
    -0.67
    POSITIVE LOGITS
    itudinal
    0.84
     diameter
    0.82
     taller
    0.76
     tall
    0.75
     inches
    0.75
    hops
    0.73
     separating
    0.73
    !/
    0.72
     thick
    0.72
     inch
    0.67
    Activations Density 0.012%

    No Known Activations