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. 9-RES-JB
    6. 10815
    Prev
    Next
    INDEX
    Explanations

    first person singular pronouns followed by verbs

    oai_token-act-pair · gpt-3.5-turbo

    the pronoun "I" and related first-person expressions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Vin
    -0.69
     Weird
    -0.68
     Bugs
    -0.64
     Takeru
    -0.64
     Mig
    -0.63
     trolling
    -0.63
     trailers
    -0.62
    opus
    -0.62
     Rolls
    -0.61
    Mech
    -0.61
    POSITIVE LOGITS
    'm
    1.31
     congratulate
    1.24
     am
    1.23
     hereby
    1.23
     apologise
    1.15
     apologize
    1.12
     assure
    1.08
     commend
    1.05
    've
    1.05
     respectfully
    1.04
    Activations Density 0.269%

    No Known Activations