© 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. 9-RES-JB
    11. 13656
    Prev
    Next
    INDEX
    Explanations

    pronouns indicating actions or companionship

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "he and [number] [plural noun]" indicating a collective action or involvement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    Not in Any Lists

    No Comments

    Negative Logits
    cms
    -0.69
    Reviewer
    -0.66
     disapp
    -0.65
    Ô
    -0.64
    .–
    -0.63
    different
    -0.62
    ombo
    -0.62
    trop
    -0.62
    Blocks
    -0.60
    Vers
    -0.59
    POSITIVE LOGITS
     others
    1.15
     fellow
    1.10
     colleagues
    1.07
     other
    0.90
     his
    0.90
     colleague
    0.87
     friends
    0.82
     Associates
    0.82
     pals
    0.82
     coworkers
    0.81
    Activations Density 0.118%

    No Known Activations