© 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. 0-RES-JB
    11. 12564
    Prev
    Next
    INDEX
    Explanations

    keywords related to energy sources and technology

    oai_token-act-pair · gpt-3.5-turbo

    themes related to burnout in the context of technology and its impact

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    urd
    -0.80
    sd
    -0.65
    thood
    -0.65
    irth
    -0.64
    atch
    -0.64
    otom
    -0.64
    onso
    -0.64
     breadth
    -0.63
    rint
    -0.63
    amy
    -0.62
    POSITIVE LOGITS
    hower
    0.79
    âķIJ
    0.75
    ²¾
    0.71
     Simulator
    0.71
    çĭ
    0.69
    ãĥķãĤ©
    0.68
     contractual
    0.67
    stretched
    0.66
     mosqu
    0.65
     eleph
    0.63
    Activations Density 0.000%

    No Known Activations