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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 7-RES-JB
    6. 597
    Prev
    Next
    INDEX
    Explanations

    conjunctions and phrases indicating reasoning or argumentation

    oai_token-act-pair · gpt-3.5-turbo

    instances of commas or punctuation that suggest complex or multi-part statements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    asma
    -0.80
    iple
    -0.78
    uber
    -0.70
    rosse
    -0.69
    atars
    -0.68
    umen
    -0.67
    ogly
    -0.66
    enne
    -0.66
    hatt
    -0.65
    chell
    -0.65
    POSITIVE LOGITS
     namely
    1.28
     lest
    1.24
     thereby
    1.16
     albeit
    1.15
    channelAvailability
    1.08
     whereby
    1.05
     insofar
    1.05
     though
    1.04
     notwithstanding
    1.01
     however
    0.99
    Activations Density 0.451%

    No Known Activations