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. 5463
    Prev
    Next
    INDEX
    Explanations

    texts referring to individuals holding the position of "senior fellow"

    oai_token-act-pair · gpt-3.5-turbo

    references to academic or professional titles, specifically "fellow" positions

    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
     DRAG
    -0.77
    ARA
    -0.74
    DEN
    -0.62
     Sorceress
    -0.61
     vend
    -0.60
     annexed
    -0.60
     nerv
    -0.59
     collateral
    -0.59
    riages
    -0.59
    photos
    -0.59
    POSITIVE LOGITS
    heastern
    0.78
    cliffe
    0.77
    ellow
    0.76
    pole
    0.74
    rored
    0.74
    ected
    0.73
     laureate
    0.72
    ector
    0.72
    elaide
    0.72
    ļéĨĴ
    0.71
    Activations Density 0.011%

    No Known Activations