© 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. 1-RES-JB
    11. 15636
    Prev
    Next
    INDEX
    Explanations

    phrases related to solar energy

    oai_token-act-pair · gpt-3.5-turbo

    references to photovoltaic technology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    HI
    -0.72
    IZ
    -0.70
     TI
    -0.69
    brance
    -0.67
    ulz
    -0.66
    endi
    -0.64
    [/
    -0.63
    IAN
    -0.62
     Plat
    -0.61
    OULD
    -0.61
    POSITIVE LOGITS
    Ô
    0.71
     Collider
    0.68
    cles
    0.68
    cule
    0.66
    Lib
    0.65
    acular
    0.65
    hawk
    0.65
    omed
    0.64
    Crash
    0.62
    ghazi
    0.61
    Activations Density 0.000%

    No Known Activations