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. 11-RES-JB
    6. 20039
    Prev
    Next
    INDEX
    Explanations

    comparisons of being ahead or behind in different situations

    oai_token-act-pair · gpt-3.5-turbo

    comparisons of progress or status between entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĥ¼ãĥĨãĤ£
    -0.73
     severed
    -0.61
    elf
    -0.60
    Empty
    -0.59
    iku
    -0.56
     Rye
    -0.55
     emptied
    -0.55
    empty
    -0.54
    uffs
    -0.54
    Closure
    -0.54
    POSITIVE LOGITS
     technologically
    1.19
     academ
    1.12
     financially
    0.99
     economically
    0.98
     athlet
    0.94
     geographically
    0.88
     nationally
    0.83
     defensively
    0.83
     ideologically
    0.82
     in
    0.82
    Activations Density 0.233%

    No Known Activations