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. 6867
    Prev
    Next
    INDEX
    Explanations

    the word "Lie" or variations of it

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the name "Lie" and its variants, likely indicating discussions related to a person or concept associated with that name

    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
    atform
    -0.68
    iaries
    -0.68
     Dull
    -0.66
     oun
    -0.64
    icable
    -0.64
    axter
    -0.63
    arthy
    -0.63
    icate
    -0.63
    oulos
    -0.63
    irlf
    -0.62
    POSITIVE LOGITS
    utenant
    1.55
    berman
    1.03
    glers
    0.94
    bro
    0.92
    bers
    0.90
    yer
    0.89
    ÃŁ
    0.89
    llan
    0.89
    ller
    0.86
    uten
    0.86
    Activations Density 0.047%

    No Known Activations