© 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. 4-RES-JB
    11. 7202
    Prev
    Next
    INDEX
    Explanations

    words related to energy and revitalization

    oai_token-act-pair · gpt-3.5-turbo

    words related to energy, upliftment, and revitalization

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

    No Comments

    Negative Logits
     Settlement
    -0.65
    Ùĩ
    -0.64
     Geneva
    -0.64
     deviations
    -0.64
     mishand
    -0.64
     barrel
    -0.62
     Errors
    -0.62
    Exec
    -0.62
     LAW
    -0.61
    ordan
    -0.61
    POSITIVE LOGITS
    itialized
    1.19
    issance
    0.91
    ament
    0.90
    enment
    0.88
    anc
    0.87
    upt
    0.84
    etsk
    0.83
    ating
    0.83
    ixir
    0.81
    strument
    0.81
    Activations Density 0.022%

    No Known Activations