© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 6-RES-JB
    6. 1359
    Prev
    Next
    INDEX
    Explanations

    legal and bureaucratic terms related to matters of governance and investigation

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to involvement and participation in various issues

    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
    abre
    -0.77
    ritical
    -0.72
    theless
    -0.71
    inder
    -0.68
    only
    -0.65
     kidding
    -0.64
    inders
    -0.64
    taboola
    -0.64
    ander
    -0.64
    identally
    -0.64
    POSITIVE LOGITS
     Mankind
    0.68
     PCs
    0.67
     Celt
    0.64
     Magicka
    0.63
     Illum
    0.62
     Alc
    0.62
     SCP
    0.60
     humankind
    0.59
     Fields
    0.59
     Ascension
    0.58
    Activations Density 0.457%

    No Known Activations