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. 11-RES-JB
    6. 16031
    Prev
    Next
    INDEX
    Explanations

    phrases containing the word "best."

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate the best solutions or options for various situations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    him
    -0.73
    ivated
    -0.71
    ipel
    -0.68
    ustom
    -0.68
    chi
    -0.66
    gian
    -0.66
    imi
    -0.66
    hig
    -0.65
    Ship
    -0.65
    clair
    -0.65
    POSITIVE LOGITS
     way
    1.38
     thing
    1.29
     solution
    1.21
     recourse
    1.19
     antidote
    1.18
     remedy
    1.18
     analogy
    1.15
     answer
    1.15
     explanation
    1.13
     advice
    1.09
    Activations Density 0.110%

    No Known Activations