© 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. 14569
    Prev
    Next
    INDEX
    Explanations

    phrases related to promises or commitments

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "promised."

    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
    pmwiki
    -1.01
    Reviewer
    -0.74
    wx
    -0.74
    aho
    -0.73
    isol
    -0.72
    cation
    -0.69
    sin
    -0.68
    etc
    -0.68
    éĸ
    -0.67
    andem
    -0.67
    POSITIVE LOGITS
    itivity
    0.77
    fulness
    0.73
     confidentiality
    0.73
     repeatedly
    0.71
    llor
    0.69
     encour
    0.67
     forgiveness
    0.64
    ebus
    0.64
     Delivery
    0.62
     assurances
    0.62
    Activations Density 0.043%

    No Known Activations