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. 1-RES-JB
    6. 12612
    Prev
    Next
    INDEX
    Explanations

    words related to specific technical terms or jargon

    oai_token-act-pair · gpt-3.5-turbo

    words related to specific biological or geographical terms, particularly those involving 'ular' roots

    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
     Wass
    -0.80
     Logged
    -0.72
     unpublished
    -0.71
    externalActionCode
    -0.69
     Meat
    -0.68
    Veter
    -0.68
    EW
    -0.68
    ACH
    -0.67
    displayText
    -0.67
     Beef
    -0.67
    POSITIVE LOGITS
    ular
    1.80
    ularity
    1.31
    ULAR
    0.91
    ciating
    0.90
    itionally
    0.88
    ulously
    0.86
    ical
    0.86
    otine
    0.86
    itional
    0.84
    icate
    0.82
    Activations Density 0.010%

    No Known Activations