© 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. 13524
    Prev
    Next
    INDEX
    Explanations

    phrases related to various topics like movies, sports, and current events

    oai_token-act-pair · gpt-3.5-turbo

    indicators of market trends and activity

    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
    ilet
    -0.53
     Slate
    -0.51
    vernment
    -0.49
    ottage
    -0.49
     Hurt
    -0.47
     Breed
    -0.46
     Revision
    -0.46
    ortium
    -0.46
     Zup
    -0.46
     Canaver
    -0.45
    POSITIVE LOGITS
     theirs
    0.56
     manageable
    0.54
    wcs
    0.51
     stagnant
    0.51
    izons
    0.51
     deems
    0.47
    ctic
    0.47
    inge
    0.47
    %.
    0.46
     otherwise
    0.45
    Activations Density 1.517%

    No Known Activations