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

    Neuronpedia

    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. 2442
    Prev
    Next
    INDEX
    Explanations

    possessive pronouns followed by a plural noun

    oai_token-act-pair · gpt-3.5-turbo

    references to specific individuals and their roles or contributions

    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
    trop
    -0.89
    mination
    -0.88
    Vers
    -0.80
    VER
    -0.78
    Texture
    -0.78
    Reviewer
    -0.76
    代
    -0.74
    FY
    -0.73
    Limit
    -0.72
    UL
    -0.71
    POSITIVE LOGITS
     cohorts
    1.36
     colleagues
    1.27
     allies
    1.25
     wife
    1.16
     il
    1.14
     associates
    1.14
     successors
    1.11
     fellow
    1.10
     crew
    1.10
     buddies
    1.09
    Activations Density 0.108%

    No Known Activations