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

    Neuronpedia

    Jacobian LensNEW
    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. 14565
    Prev
    Next
    INDEX
    Explanations

    the word "or" as a crucial element in a statement

    oai_token-act-pair · gpt-3.5-turbo

    conditional phrases and conjunctions that indicate alternatives or options

    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
     "$:/
    -0.66
     Arri
    -0.65
    Zone
    -0.65
     Mage
    -0.63
    andise
    -0.61
     Tru
    -0.60
     Composite
    -0.60
     Detail
    -0.59
     Murd
    -0.59
     Objects
    -0.58
    POSITIVE LOGITS
    pless
    0.75
    lez
    0.74
    æĸ¹
    0.72
    rouse
    0.70
    andom
    0.69
    unia
    0.69
    minus
    0.66
    send
    0.65
     homework
    0.64
    unal
    0.64
    Activations Density 0.211%

    No Known Activations