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. 10-RES-JB
    6. 11868
    Prev
    Next
    INDEX
    Explanations

    phrases related to technical specifications or descriptions

    oai_token-act-pair · gpt-3.5-turbo

    phrases and terms related to classifications and types, particularly focusing on "of."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    FUL
    -0.63
     wrench
    -0.63
     birthplace
    -0.58
    WARE
    -0.58
     amaz
    -0.58
     Rubin
    -0.57
     ridic
    -0.57
    ++++++++++++++++
    -0.56
     stripping
    -0.56
     Pont
    -0.56
    POSITIVE LOGITS
    eatures
    1.31
    actory
    1.26
    requency
    1.20
    unction
    1.14
    riend
    1.12
    actor
    1.11
    estival
    1.10
    ascist
    1.10
    action
    1.09
    ocus
    1.08
    Activations Density 0.036%

    No Known Activations