© 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. 3-RES-JB
    11. 13634
    Prev
    Next
    INDEX
    Explanations

    words related to beams or beam-like structures

    oai_token-act-pair · gpt-3.5-turbo

    references to beams of light or energy

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    é»Ĵ
    -0.81
    phis
    -0.72
    DIT
    -0.71
    uana
    -0.69
    hiro
    -0.68
    afort
    -0.67
    ADRA
    -0.66
    POL
    -0.66
    monary
    -0.64
    ascular
    -0.63
    POSITIVE LOGITS
     beams
    1.02
     beam
    0.94
    casters
    0.85
    eners
    0.81
    efully
    0.81
    glass
    0.81
    beam
    0.79
     ray
    0.78
     Beam
    0.76
     barr
    0.76
    Activations Density 0.012%

    No Known Activations