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. 23607
    Prev
    Next
    INDEX
    Explanations

    words related to the concept of following or coming behind something/someone

    oai_token-act-pair · gpt-3.5-turbo

    references to trailing or trailing margins in various contexts

    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
    ilaterally
    -0.73
     deal
    -0.72
    ylum
    -0.72
    iza
    -0.71
    ocker
    -0.70
    uckle
    -0.69
    deal
    -0.69
    thodox
    -0.69
    idence
    -0.66
    immer
    -0.66
    POSITIVE LOGITS
     trailing
    1.06
    bare
    0.93
    beat
    0.88
     trailed
    0.87
    rils
    0.73
    byss
    0.68
    duration
    0.66
    ttes
    0.66
     Spaces
    0.65
     whistle
    0.65
    Activations Density 0.007%

    No Known Activations