© 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. 7146
    Prev
    Next
    INDEX
    Explanations

    terms related to conflict or competition

    oai_token-act-pair · gpt-3.5-turbo
    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
    WARD
    -0.72
     Chocobo
    -0.71
     Mayer
    -0.67
    chev
    -0.64
    bleacher
    -0.63
    OHN
    -0.63
     Bloom
    -0.61
    yss
    -0.61
     Penny
    -0.60
     Compass
    -0.57
    POSITIVE LOGITS
    idential
    0.93
    uted
    0.92
    irmed
    0.90
    iliation
    0.89
    ictions
    0.88
    aints
    0.86
    iction
    0.83
    itution
    0.83
    irmation
    0.82
    ruction
    0.82
    Activations Density 0.071%

    No Known Activations