© 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. 11526
    Prev
    Next
    INDEX
    Explanations

    instances of the word "slight" and variations of it

    oai_token-act-pair · gpt-3.5-turbo

    references to minimal changes or minor differences

    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
    ourses
    -0.78
    ilk
    -0.77
    utics
    -0.74
    ridor
    -0.69
    ©¶æ
    -0.69
     dearly
    -0.67
    apter
    -0.66
    agents
    -0.65
    model
    -0.64
     Methods
    -0.64
    POSITIVE LOGITS
     uptick
    1.24
     annoyance
    1.11
     inconvenience
    1.11
     deviation
    1.09
     alteration
    1.08
     exaggeration
    1.08
     resemblance
    1.08
     interruption
    1.01
     breeze
    1.01
     deviations
    1.00
    Activations Density 0.081%

    No Known Activations