© 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. 8-RES-JB
    11. 3102
    Prev
    Next
    INDEX
    Explanations

    pronouns and names of individuals

    oai_token-act-pair · gpt-3.5-turbo

    the repetition of pronouns referring to individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ruciating
    -0.75
    Reviewer
    -0.73
     Globe
    -0.72
    opolis
    -0.71
     Concord
    -0.68
     Claire
    -0.68
    ogue
    -0.68
     Hunting
    -0.68
     Thrones
    -0.66
    arios
    -0.64
    POSITIVE LOGITS
    'll
    1.30
    're
    1.13
    'd
    1.12
     ought
    1.00
     could
    0.99
     might
    0.96
     forgot
    0.94
     qualifies
    0.92
     SHOULD
    0.91
     would
    0.90
    Activations Density 0.218%

    No Known Activations