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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 22217
    Prev
    Next
    INDEX
    Explanations

    ways to improve or enhance various aspects or systems, such as making something more reliable, efficient, affordable, or accessible

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "more" and its variations indicating increased quantity or improvement

    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
    ufact
    -0.74
    uckle
    -0.73
    ipment
    -0.70
    outer
    -0.68
    ENA
    -0.67
    ovie
    -0.66
    ername
    -0.66
    oresc
    -0.65
     NCT
    -0.64
    IPS
    -0.63
    POSITIVE LOGITS
     efficient
    1.13
     accessible
    1.11
     attractive
    1.09
     appealing
    1.07
     manageable
    1.03
     resilient
    0.99
     conducive
    0.98
     inclusive
    0.97
     equitable
    0.97
     effective
    0.95
    Activations Density 0.110%

    No Known Activations