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. 3802
    Prev
    Next
    INDEX
    Explanations

    uses of possessive pronouns 'its'

    oai_token-act-pair · gpt-3.5-turbo

    references to the word "its" 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
    nian
    -0.58
    aire
    -0.58
    efe
    -0.57
    **
    -0.55
     respectively
    -0.54
    bridge
    -0.53
     ---------
    -0.52
    nder
    -0.51
    hews
    -0.51
    jah
    -0.50
    POSITIVE LOGITS
     its
    2.93
     Its
    2.43
    Its
    2.31
     ITS
    1.92
     itself
    1.59
    its
    1.30
     their
    1.02
    their
    0.89
     theirs
    0.81
     it
    0.80
    Activations Density 0.126%

    No Known Activations