© 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. 2-RES-JB
    11. 19776
    Prev
    Next
    INDEX
    Explanations

    phrases related to large-scale activities or objects

    oai_token-act-pair · gpt-3.5-turbo

    references to large-scale projects or operations

    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
    ieu
    -0.71
    ournal
    -0.69
    hiro
    -0.66
    ĪĴ
    -0.66
    olkien
    -0.64
    leans
    -0.64
    ryn
    -0.64
     Indies
    -0.63
    swick
    -0.63
    iyah
    -0.62
    POSITIVE LOGITS
    scale
    1.02
     scale
    0.81
    Scale
    0.78
     replica
    0.77
     gestures
    0.75
    itized
    0.74
     instruments
    0.70
     scales
    0.68
     violations
    0.68
    form
    0.68
    Activations Density 0.013%

    No Known Activations