© 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. 13917
    Prev
    Next
    INDEX
    Explanations

    phrases emphasizing unity and solidarity

    oai_token-act-pair · gpt-3.5-turbo

    phrases emphasizing collective identity and the assertion of presence or existence

    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
    inav
    -0.76
    pmwiki
    -0.70
    ategor
    -0.69
     unfocusedRange
    -0.68
    mentioned
    -0.67
    tesy
    -0.66
    Scroll
    -0.65
    eanor
    -0.65
     (~
    -0.64
    ipeg
    -0.63
    POSITIVE LOGITS
     tired
    1.11
     proud
    1.08
     sorry
    1.01
     willing
    1.00
     committed
    0.98
     ready
    0.95
     grateful
    0.94
     glad
    0.91
     gonna
    0.91
     thankful
    0.90
    Activations Density 0.205%

    No Known Activations