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. 7-RES-JB
    6. 5879
    Prev
    Next
    INDEX
    Explanations

    descriptions of natural elements and physical sensations

    oai_token-act-pair · gpt-3.5-turbo

    descriptive language related to nature and ambient settings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    umbn
    -0.76
    ħĭ
    -0.76
    Problem
    -0.75
    itionally
    -0.75
    CLASS
    -0.72
     practition
    -0.71
    ozyg
    -0.71
    Specifically
    -0.70
    actionDate
    -0.69
    Cap
    -0.68
    POSITIVE LOGITS
     throb
    1.07
     shimmer
    1.06
     crimson
    1.00
     gle
    0.96
     sparkling
    0.94
     breeze
    0.92
     reverber
    0.92
     flakes
    0.92
     glitter
    0.91
     haze
    0.91
    Activations Density 0.503%

    No Known Activations