© 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. 20632
    Prev
    Next
    INDEX
    Explanations

    the word "colleagues"

    oai_token-act-pair · gpt-3.5-turbo

    references to collaboration or teamwork in professional contexts

    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
    sole
    -0.77
    sword
    -0.72
    seed
    -0.72
    si
    -0.69
    Ball
    -0.69
    ball
    -0.68
    sp
    -0.66
    direction
    -0.66
    foot
    -0.65
    Naz
    -0.65
    POSITIVE LOGITS
     colleagues
    1.49
     colleague
    1.22
     coworkers
    1.18
    ratulations
    1.01
     pals
    0.94
     collaborators
    0.93
     classmates
    0.91
    ĸļ
    0.89
    mates
    0.81
     roomm
    0.81
    Activations Density 0.017%

    No Known Activations