© 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. 1-RES-JB
    11. 9529
    Prev
    Next
    INDEX
    Explanations

    instances of collaboration between entities or individuals

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "collaboration."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Sabha
    -0.84
     Centauri
    -0.70
    akia
    -0.70
    nn
    -0.70
    leigh
    -0.69
    gyn
    -0.67
    ther
    -0.66
    missing
    -0.66
    gger
    -0.66
    teen
    -0.65
    POSITIVE LOGITS
     collaborations
    1.28
     collaborators
    1.26
     collaboration
    1.25
     collaborator
    1.20
     collaborating
    1.08
     collaborative
    1.01
     collaborated
    0.99
     collaborate
    0.98
     collabor
    0.94
     Collabor
    0.90
    Activations Density 0.013%

    No Known Activations