© 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. 11881
    Prev
    Next
    INDEX
    Explanations

    phrases related to legal or official matters

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating evaluations or considerations related to various subjects

    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
    avorite
    -0.80
     helicop
    -0.75
    egg
    -0.73
     tatt
    -0.66
     Sieg
    -0.66
     Pengu
    -0.66
     Huck
    -0.65
     submar
    -0.65
     Straw
    -0.64
     suspic
    -0.63
    POSITIVE LOGITS
    unia
    0.82
    ments
    0.81
    eous
    0.81
    ardless
    0.76
    range
    0.75
    ertain
    0.73
    rection
    0.72
     regards
    0.72
    equality
    0.71
    ibility
    0.71
    Activations Density 0.031%

    No Known Activations