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. 2-RES-JB
    6. 272
    Prev
    Next
    INDEX
    Explanations

    the adverb "particularly"

    oai_token-act-pair · gpt-4-turbo

    adverbs that describe to what degree something is happening

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "particularly"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ocene
    -0.81
    ÅĤ
    -0.79
    URE
    -0.69
     Laos
    -0.66
    lyn
    -0.65
    ocracy
    -0.65
    him
    -0.65
     Ferry
    -0.64
     Viet
    -0.64
    viron
    -0.64
    POSITIVE LOGITS
     noteworthy
    0.96
     advantageous
    0.92
     susceptible
    0.92
     tailored
    0.85
     identifiable
    0.84
     frequ
    0.84
     egregious
    0.82
     benefited
    0.81
     suited
    0.81
     noticeable
    0.81
    Activations Density 0.020%

    No Known Activations