© 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. 22567
    Prev
    Next
    INDEX
    Explanations

    mentions of improvement or comparison for different scenarios, with a preference towards the concept of "better"

    oai_token-act-pair · gpt-3.5-turbo

    the word "better" and its variations

    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
     Pione
    -0.73
    ategory
    -0.66
    cha
    -0.65
    sup
    -0.64
    ette
    -0.63
    cano
    -0.62
    amine
    -0.61
    kaya
    -0.61
    umo
    -0.60
    ums
    -0.59
    POSITIVE LOGITS
     than
    1.31
    than
    1.09
     suited
    1.08
     behaved
    1.04
     Than
    1.03
    ment
    0.95
     acquainted
    0.94
     equipped
    0.86
    ments
    0.81
     luck
    0.80
    Activations Density 0.067%

    No Known Activations