© 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. 10-RES-JB
    11. 16029
    Prev
    Next
    INDEX
    Explanations

    words related to the concept of "replacing" or "rearranging"

    oai_token-act-pair · gpt-3.5-turbo

    terms related to negation or undesirable qualities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ĸļ
    -0.74
     Wellington
    -0.67
     Warwick
    -0.66
     ribbon
    -0.64
     Solitaire
    -0.61
    STD
    -0.61
     Hawth
    -0.61
     Mayer
    -0.60
     Wonderland
    -0.59
    boxing
    -0.59
    POSITIVE LOGITS
    itiveness
    1.15
    iencies
    1.14
    itive
    1.13
    itions
    1.13
    itely
    1.11
    ishable
    0.99
    atory
    0.95
    utation
    0.95
    ciation
    0.94
    ileged
    0.92
    Activations Density 0.069%

    No Known Activations