© 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. 9-RES-JB
    11. 4902
    Prev
    Next
    INDEX
    Explanations

    names of individuals

    oai_token-act-pair · gpt-3.5-turbo

    proper nouns, particularly names of people

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Last name of Name2 in "Name1 and Name2"

    Explanation Uploaded by User
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    •L9 resid features following 'and'

    No Comments

    Negative Logits
    itiz
    -0.62
    itiveness
    -0.59
    needs
    -0.59
    ":"/
    -0.58
     Flavoring
    -0.56
     itself
    -0.56
    patient
    -0.54
     snipp
    -0.53
    itized
    -0.52
     Registrar
    -0.52
    POSITIVE LOGITS
     respectively
    1.72
     alike
    1.28
     jointly
    1.03
     are
    0.97
     were
    0.96
     together
    0.95
    both
    0.91
    each
    0.90
     aren
    0.89
     mutually
    0.88
    Activations Density 0.201%

    No Known Activations