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. 0-RES-JB
    6. 4346
    Prev
    Next
    INDEX
    Explanations

    words related to growth and development

    oai_token-act-pair · gpt-3.5-turbo

    linguistic expressions of growth or transformation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     TABLE
    -0.64
     conflicted
    -0.63
     contradictions
    -0.63
    ãģ§
    -0.57
     EA
    -0.57
     sur
    -0.56
    steam
    -0.56
     tables
    -0.56
     glaciers
    -0.56
     Spice
    -0.56
    POSITIVE LOGITS
    oming
    4.73
    oms
    2.02
    omed
    1.92
    omes
    1.31
    ome
    1.28
    omers
    1.23
    omic
    1.22
    omen
    1.21
    omm
    1.17
    omy
    1.16
    Activations Density 0.007%

    No Known Activations