© 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. 2-RES-JB
    11. 17627
    Prev
    Next
    INDEX
    Explanations

    terms related to electronic data and storage devices

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating transformation or change in state

    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
    ĸļ
    -1.02
    paio
    -0.84
    phia
    -0.79
     Marse
    -0.70
     Pharaoh
    -0.70
     Celest
    -0.68
     Archdemon
    -0.66
     paramedics
    -0.66
    ĪĴ
    -0.66
    ĺħ
    -0.65
    POSITIVE LOGITS
    ³³³
    0.84
    swick
    0.79
    reading
    0.77
    lishes
    0.76
    WI
    0.75
    Lower
    0.72
    DIS
    0.72
    Books
    0.68
    ilk
    0.68
    Õ
    0.68
    Activations Density 0.000%

    No Known Activations