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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 21767
    Prev
    Next
    INDEX
    Explanations

    personal pronouns referring to unspecified entities

    oai_token-act-pair · gpt-3.5-turbo

    pronouns and their forms in sentences

    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
     Amen
    -0.83
    Newsletter
    -0.72
     Ago
    -0.71
     Definition
    -0.64
    Marginal
    -0.64
     Month
    -0.63
     Pages
    -0.63
     Club
    -0.61
     Article
    -0.60
     Member
    -0.60
    POSITIVE LOGITS
    bsite
    0.99
    ngth
    0.89
    !).
    0.82
    ardless
    0.79
    ?).
    0.79
    arently
    0.79
    agine
    0.76
    %).
    0.73
    FORE
    0.72
    self
    0.71
    Activations Density 0.228%

    No Known Activations