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. 9
    Prev
    Next
    INDEX
    Explanations

    mentions of "different" aspects or variations within the context of various topics or subjects

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "different" and its variations in various contexts

    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
    WARD
    -0.73
     âĨij
    -0.72
    âĢł
    -0.71
    ³³³³³³³³³³³³³³³³
    -0.69
    Never
    -0.67
     COUR
    -0.63
    QU
    -0.63
     ALWAYS
    -0.63
    timer
    -0.62
     wink
    -0.62
    POSITIVE LOGITS
    iating
    1.82
    iates
    1.53
     kinds
    1.36
    iations
    1.31
    iated
    1.23
    ials
    1.23
    iator
    1.18
     types
    1.09
    ially
    1.09
    iation
    1.07
    Activations Density 0.041%

    No Known Activations