© 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. 1-RES-JB
    11. 20026
    Prev
    Next
    INDEX
    Explanations

    personal pronouns preceding verbs, particularly the pronoun "it" before verbs

    oai_token-act-pair · gpt-3.5-turbo

    the pronoun "it."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Orn
    -0.68
    hips
    -0.68
     Dayton
    -0.66
    Priv
    -0.66
     Lar
    -0.65
     Anat
    -0.64
     Breast
    -0.64
     Superior
    -0.64
     Friend
    -0.63
     Cour
    -0.63
    POSITIVE LOGITS
    alian
    1.16
    self
    0.99
    ueller
    0.99
    unes
    0.97
    asca
    0.92
    chy
    0.84
    hers
    0.80
    zbollah
    0.80
    heit
    0.79
    geist
    0.77
    Activations Density 0.419%

    No Known Activations