© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 11-RES-JB
    11. 12143
    Prev
    Next
    INDEX
    Explanations

    phrases related to teams working together on challenging tasks

    oai_token-act-pair · gpt-3.5-turbo

    references to teamwork and collaboration in creative projects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     condol
    -0.95
     prohibitions
    -0.77
     avoidance
    -0.75
     deterrence
    -0.73
     advertisements
    -0.72
    negative
    -0.72
    False
    -0.72
     Celeb
    -0.72
     evasion
    -0.71
    interstitial
    -0.71
    POSITIVE LOGITS
     collaborate
    1.23
     collabor
    1.21
     collaborating
    1.19
     brainstorm
    1.12
     designing
    1.10
     prototyp
    1.07
    Working
    1.06
     working
    1.04
     collaborative
    1.01
     collaborated
    1.01
    Activations Density 0.605%

    No Known Activations