Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 7521
    Prev
    Next
    INDEX
    Explanations

    phrases containing first person pronouns

    oai_token-act-pair · gpt-3.5-turbo

    first-person pronouns and expressions of personal opinions or expectations

    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
     Gutenberg
    -0.73
    ibrary
    -0.68
     proto
    -0.63
     Rolls
    -0.63
     etiquette
    -0.62
     Occupations
    -0.60
    iquette
    -0.59
     selves
    -0.59
     passers
    -0.58
     hers
    -0.58
    POSITIVE LOGITS
    'm
    1.20
     guess
    1.19
     think
    1.15
     believe
    1.14
     doubt
    1.13
     suppose
    1.13
     reckon
    1.08
     hope
    1.05
     presume
    1.03
     suspect
    1.01
    Activations Density 0.184%

    No Known Activations