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. 144
    Prev
    Next
    INDEX
    Explanations

    instances where the subject is 'it is'

    oai_token-act-pair · gpt-3.5-turbo

    contractions and variations of "it is" or "it's"

    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
    /"
    -0.67
    theless
    -0.65
     beforehand
    -0.62
    ]+
    -0.59
    existent
    -0.58
     thereof
    -0.58
    ONSORED
    -0.58
     outweigh
    -0.58
    -"
    -0.57
     assail
    -0.55
    POSITIVE LOGITS
    estern
    0.78
    gae
    0.78
    resa
    0.67
     Mahjong
    0.66
     Ful
    0.63
    htaking
    0.62
     Horus
    0.60
    ibaba
    0.59
    plom
    0.59
     Tycoon
    0.58
    Activations Density 0.320%

    No Known Activations