© 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. 2-RES-JB
    11. 23650
    Prev
    Next
    INDEX
    Explanations

    terms related to interactions and collaborations with peers or coworkers

    oai_token-act-pair · gpt-3.5-turbo

    mentions of colleagues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ball
    -0.79
    sole
    -0.75
    sword
    -0.70
    direction
    -0.68
    cer
    -0.66
    si
    -0.66
    aval
    -0.65
    Shock
    -0.65
    iculture
    -0.63
    seed
    -0.62
    POSITIVE LOGITS
     colleagues
    1.23
     colleague
    1.08
     coworkers
    0.94
    ratulations
    0.84
     collaborators
    0.81
    mates
    0.78
     pals
    0.76
    hip
    0.73
     classmates
    0.73
    oneliness
    0.72
    Activations Density 0.015%

    No Known Activations