© 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. 4971
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "partner."

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "partner" and its variations connected to collaborative relationships

    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
    aston
    -0.85
    ibrary
    -0.72
    ihil
    -0.72
    anwhile
    -0.71
    ãĥ©ãĥ³
    -0.71
    iter
    -0.71
     oxide
    -0.69
    SpaceEngineers
    -0.68
    ux
    -0.68
    hazard
    -0.67
    POSITIVE LOGITS
     partner
    0.95
     partners
    0.92
    hips
    0.82
    loo
    0.69
    heses
    0.68
    hood
    0.68
     Partner
    0.68
    ries
    0.65
    cially
    0.62
    wise
    0.61
    Activations Density 0.041%

    No Known Activations