© 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. 3547
    Prev
    Next
    INDEX
    Explanations

    words related to identifying and resolving problems

    oai_token-act-pair · gpt-3.5-turbo

    references to issues that need to be resolved or corrected

    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
    NetMessage
    -0.88
    ographic
    -0.75
    ographies
    -0.73
    Champ
    -0.69
     Phant
    -0.63
    CHR
    -0.62
     unprotected
    -0.62
    ammy
    -0.62
     livest
    -0.61
    idav
    -0.60
    POSITIVE LOGITS
    ated
    0.94
    ysis
    0.90
    ating
    0.84
    ation
    0.84
    esty
    0.82
    num
    0.82
    ate
    0.77
    enhagen
    0.76
    eq
    0.74
    hift
    0.74
    Activations Density 0.022%

    No Known Activations