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. 4383
    Prev
    Next
    INDEX
    Explanations

    phrases or words related to providing deep understanding or knowledge

    oai_token-act-pair · gpt-3.5-turbo

    terms related to insight or understanding

    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
    olina
    -0.67
    Default
    -0.66
    erto
    -0.64
    PA
    -0.64
    mop
    -0.63
    boy
    -0.63
     Manufacturer
    -0.61
    ede
    -0.60
    ARS
    -0.60
    URA
    -0.60
    POSITIVE LOGITS
     insight
    3.38
     insights
    2.99
     insightful
    1.79
     Insight
    1.75
     clarity
    1.38
     glimpse
    1.36
     perspectives
    1.35
     understanding
    1.33
     perspective
    1.32
     intuition
    1.30
    Activations Density 0.025%

    No Known Activations