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. 6-RES-JB
    6. 18539
    Prev
    Next
    INDEX
    Explanations

    the word "too" used in various contexts

    oai_token-act-pair · gpt-3.5-turbo

    phrases containing the word "too" and associated modifiers hinting at excess or emphasis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    izen
    -0.62
    jri
    -0.61
    engers
    -0.61
     highs
    -0.60
     appro
    -0.58
     embark
    -0.57
    apons
    -0.57
    plates
    -0.56
     trending
    -0.55
     Alley
    -0.55
    POSITIVE LOGITS
    ©¶æ¥µ
    0.75
    rame
    0.74
    esta
    0.66
    Ĥ¬
    0.65
    ĨĴ
    0.63
    ··
    0.62
    atio
    0.61
    GH
    0.61
    Ĥ
    0.61
    eming
    0.59
    Activations Density 0.207%

    No Known Activations