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. 10-RES-JB
    6. 21079
    Prev
    Next
    INDEX
    Explanations

    personal reflections and insights expressed in the first person singular

    oai_token-act-pair · gpt-3.5-turbo

    first-person pronouns and self-referential statements

    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
    Delivery
    -0.75
     Pric
    -0.67
    Looks
    -0.64
     Impact
    -0.61
     totality
    -0.60
     TBD
    -0.60
     Deadline
    -0.59
     optics
    -0.59
     unspecified
    -0.58
    farious
    -0.58
    POSITIVE LOGITS
    've
    1.25
    'm
    1.20
     suppose
    1.09
    deals
    1.08
     prefer
    1.07
     cringe
    1.05
    ronic
    1.05
     rarely
    1.03
     vividly
    1.03
     am
    1.03
    Activations Density 0.250%

    No Known Activations