© 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. 2-RES-JB
    11. 6591
    Prev
    Next
    INDEX
    Explanations

    references to marketing and business strategies, specifically related to the term "Direct."

    oai_token-act-pair · gpt-3.5-turbo

    references to direct television services and related programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Schne
    -0.76
    OPLE
    -0.73
     Kaufman
    -0.72
     Wilde
    -0.72
    anners
    -0.71
    OAD
    -0.71
     Petersburg
    -0.69
    nesota
    -0.66
    astical
    -0.66
    ACK
    -0.65
    POSITIVE LOGITS
    cuts
    1.02
    direct
    0.92
     Direct
    0.89
    ions
    0.89
    Direct
    0.89
    lined
    0.86
    irect
    0.85
    htaking
    0.85
    cut
    0.80
    ories
    0.80
    Activations Density 0.011%

    No Known Activations