© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 10-RES-JB
    11. 9919
    Prev
    Next
    INDEX
    Explanations

    personal pronouns followed by some form of past tense verb

    oai_token-act-pair · gpt-3.5-turbo

    first-person pronouns indicating personal experiences and emotions

    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
    utical
    -0.79
     totality
    -0.71
    INGTON
    -0.65
    ãĤ¼
    -0.65
     ABV
    -0.63
    pires
    -0.62
     layoffs
    -0.61
    isite
    -0.61
    category
    -0.61
     municipality
    -0.60
    POSITIVE LOGITS
    'm
    1.12
     laughed
    1.10
     guess
    1.09
     suppose
    1.07
     thanked
    1.04
     kissed
    1.03
     presume
    1.03
     hugged
    1.02
     assume
    0.97
     joked
    0.96
    Activations Density 0.173%

    No Known Activations