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. 10-RES-JB
    6. 2355
    Prev
    Next
    INDEX
    Explanations

    first-person pronouns and related verb phrases indicating personal experiences and reflections

    oai_token-act-pair · gpt-3.5-turbo

    instances of the pronoun "I" and expressions of personal experiences or opinions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ahead
    -0.69
     embodiments
    -0.69
    pires
    -0.69
     innovations
    -0.67
    ãĤ¼
    -0.66
     revisions
    -0.64
     expansions
    -0.64
     enhancements
    -0.64
    Creat
    -0.64
     mastery
    -0.62
    POSITIVE LOGITS
     cried
    1.19
    've
    1.10
     wonder
    1.10
     pray
    1.09
     begged
    1.04
     screamed
    1.04
     prayed
    1.03
     cringe
    1.03
     weep
    1.01
     pity
    1.01
    Activations Density 0.262%

    No Known Activations