Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 9-RES-JB
    6. 9906
    Prev
    Next
    INDEX
    Explanations

    phrases that include specific symbols and show a mix of verbs and nouns

    oai_token-act-pair · gpt-3.5-turbo

    phrases or terms related to recognition or acknowledgment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     consequential
    -0.69
     characteristic
    -0.69
     Tsukuyomi
    -0.68
     hostile
    -0.65
     Ninth
    -0.65
     Slug
    -0.62
     fascinating
    -0.61
     incendiary
    -0.60
     valuable
    -0.60
     lif
    -0.59
    POSITIVE LOGITS
    create
    1.41
    make
    1.27
    apply
    1.23
    activate
    1.22
    rouse
    1.22
    take
    1.21
    imize
    1.20
    have
    1.19
    raise
    1.17
    give
    1.17
    Activations Density 0.181%

    No Known Activations