© 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. 0-RES-JB
    11. 19047
    Prev
    Next
    INDEX
    Explanations

    terms related to inefficiency and difficulties within systems or processes

    oai_token-act-pair · gpt-3.5-turbo

    terms related to efficiency and abilities

    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
    ized
    -0.71
     kissed
    -0.65
     Remix
    -0.65
     kiss
    -0.62
     raped
    -0.61
    kiss
    -0.61
     Ped
    -0.60
     Kiss
    -0.59
    ãĥŃ
    -0.58
    tta
    -0.57
    POSITIVE LOGITS
    abilities
    2.91
    effic
    2.90
    efficiency
    2.67
    ordinate
    1.57
    activity
    1.38
    qus
    1.37
    activation
    1.22
    anity
    1.03
    availability
    1.02
    confidence
    1.02
    Activations Density 0.044%

    No Known Activations