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. 6-RES-JB
    6. 1872
    Prev
    Next
    INDEX
    Explanations

    phrases related to communication and influence, especially using the phrase "word of mouth"

    oai_token-act-pair · gpt-3.5-turbo

    references to "word of mouth" and its implications 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
    iage
    -0.82
    nels
    -0.70
    hement
    -0.69
    erella
    -0.69
    ilial
    -0.68
    ieu
    -0.67
    amins
    -0.65
    ovember
    -0.65
    monary
    -0.65
    emale
    -0.63
    POSITIVE LOGITS
     aloud
    0.83
     encoding
    0.70
     acronym
    0.67
    bern
    0.64
     Cthulhu
    0.62
     recommendation
    0.61
    ר
    0.61
     poem
    0.60
     wisdom
    0.60
     sober
    0.59
    Activations Density 0.135%

    No Known Activations