© 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. 11-RES-JB
    11. 3758
    Prev
    Next
    INDEX
    Explanations

    phrases related to conflict or opposition

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to games and competition

    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
     otherwise
    -0.60
     Integrity
    -0.59
     Administration
    -0.58
     hardened
    -0.57
     facet
    -0.57
     improved
    -0.56
     Woodward
    -0.56
     Meadows
    -0.56
     Weekly
    -0.56
     Austral
    -0.56
    POSITIVE LOGITS
    bang
    1.14
    ups
    1.14
    toe
    1.03
    mob
    1.03
    up
    1.01
    buck
    1.01
    your
    0.98
    shit
    0.96
    trap
    0.96
    inducing
    0.93
    Activations Density 0.071%

    No Known Activations