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. 11-RES-JB
    6. 22923
    Prev
    Next
    INDEX
    Explanations

    pronouns followed by the verb "to be"

    oai_token-act-pair · gpt-3.5-turbo

    the pronoun "it" in various contexts, often used to refer back to previously mentioned concepts or subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Gifts
    -0.65
     Buck
    -0.62
     Vault
    -0.60
    Interstitial
    -0.58
     Saying
    -0.58
     Westminster
    -0.57
    Finish
    -0.57
    package
    -0.56
    _>
    -0.56
     Canter
    -0.56
    POSITIVE LOGITS
     appears
    1.25
     seems
    1.23
     turns
    1.17
     transpired
    1.14
     emerges
    1.09
    anium
    1.01
     is
    1.00
     beh
    0.99
     becomes
    0.98
     should
    0.96
    Activations Density 0.114%

    No Known Activations