© 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. 6-RES-JB
    11. 13733
    Prev
    Next
    INDEX
    Explanations

    words related to negative connotations or controversial topics

    oai_token-act-pair · gpt-3.5-turbo

    variations of the root word "rep" indicating repetition or replication in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Whitman
    -0.67
     Dragonbound
    -0.65
     Creed
    -0.65
     Dahl
    -0.61
     Glou
    -0.60
     Powell
    -0.60
     Vaughan
    -0.59
     mercury
    -0.59
     Hastings
    -0.59
     Brah
    -0.58
    POSITIVE LOGITS
    ciation
    0.97
    posed
    0.91
    posing
    0.88
    cipled
    0.88
    ciating
    0.84
    lisher
    0.84
    nant
    0.83
    amins
    0.81
    lishing
    0.80
    aration
    0.80
    Activations Density 0.062%

    No Known Activations