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. 8-RES-JB
    6. 21041
    Prev
    Next
    INDEX
    Explanations

    personal pronouns and verbs related to communication or documentation

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the first-person pronoun "I" and related verbs indicating personal thoughts or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Vin
    -0.72
     Takeru
    -0.71
     Semi
    -0.69
     Hybrid
    -0.68
     Vie
    -0.66
     Mig
    -0.65
     passers
    -0.64
     Cinderella
    -0.64
     OG
    -0.63
     Maid
    -0.62
    POSITIVE LOGITS
    'm
    1.22
     personally
    1.12
     congratulate
    1.09
     am
    1.08
     commend
    1.04
     intend
    1.03
     hereby
    1.03
     sincerely
    1.01
     propose
    0.99
     reiterate
    0.99
    Activations Density 0.281%

    No Known Activations