© 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. 17795
    Prev
    Next
    INDEX
    Explanations

    the phrase "the best way to."

    oai_token-act-pair · gpt-3.5-turbo

    phrases that suggest the best method or approach to accomplish various tasks

    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
    usters
    -0.98
    ĸļ
    -0.80
    uster
    -0.80
    itor
    -0.73
    oubted
    -0.73
    omore
    -0.72
    etheus
    -0.69
    icio
    -0.69
    lict
    -0.67
    querque
    -0.67
    POSITIVE LOGITS
    finding
    1.05
    fare
    1.04
    ward
    0.83
    finder
    0.82
    forward
    0.80
     forward
    0.78
    PASS
    0.76
    point
    0.75
    LI
    0.72
    bm
    0.70
    Activations Density 0.045%

    No Known Activations