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. 23795
    Prev
    Next
    INDEX
    Explanations

    terms related to compactness or small size

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of 'compactness' in various contexts

    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
    Downloadha
    -0.90
    CVE
    -0.82
    opoulos
    -0.75
    olkien
    -0.71
    govtrack
    -0.71
    uthor
    -0.68
    hod
    -0.68
    ãĤ´ãĥ³
    -0.67
    hin
    -0.66
    afia
    -0.66
    POSITIVE LOGITS
     discs
    0.85
    arily
    0.81
     compact
    0.81
     footprint
    0.81
    ness
    0.80
     fluorescent
    0.78
    nesses
    0.77
    icut
    0.76
     Compact
    0.76
     sized
    0.75
    Activations Density 0.007%

    No Known Activations