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. 0-RES-JB
    6. 10870
    Prev
    Next
    INDEX
    Explanations

    texts where the pronoun "It" is used indicating a significant observation or action

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "It" as a subject in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    orial
    -0.70
     deceased
    -0.59
     fond
    -0.55
    ady
    -0.54
     barg
    -0.53
    eker
    -0.52
     eligible
    -0.52
     summ
    -0.51
     rank
    -0.51
    usal
    -0.51
    POSITIVE LOGITS
     It
    2.43
     Its
    1.93
    It
    1.74
     There
    1.64
     That
    1.58
     They
    1.57
     This
    1.56
    Its
    1.52
     Though
    1.45
     You
    1.42
    Activations Density 0.097%

    No Known Activations