© 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 EvalsExportsinterp-engineNEWAPI 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. 9294
    Prev
    Next
    INDEX
    Explanations

    terms related to working together or being part of a team

    oai_token-act-pair · gpt-3.5-turbo

    references to groups of people working collaboratively

    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
    uncture
    -0.71
    ension
    -0.68
    Temperature
    -0.63
     Temperature
    -0.63
     iT
    -0.63
    strength
    -0.62
    WE
    -0.61
     Rudd
    -0.60
     pH
    -0.59
     Osw
    -0.59
    POSITIVE LOGITS
     alike
    0.95
     respectively
    0.86
    axter
    0.77
    mates
    0.72
    ioned
    0.70
     embarked
    0.69
    ervatives
    0.68
    hots
    0.67
     erected
    0.66
     challeng
    0.66
    Activations Density 0.153%

    No Known Activations