© 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. 12574
    Prev
    Next
    INDEX
    Explanations

    the name "Garland" with varying levels of specificity

    oai_token-act-pair · gpt-3.5-turbo

    references to the name "Garland."

    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
     AOL
    -0.72
    OA
    -0.69
    ODUCT
    -0.68
    ×ij
    -0.66
    olitan
    -0.65
    ocol
    -0.63
    odcast
    -0.63
     Antar
    -0.62
    apy
    -0.60
     Stun
    -0.60
    POSITIVE LOGITS
     Garland
    1.11
    eering
    0.82
    rand
    0.78
    stack
    0.75
    picking
    0.72
    pole
    0.72
    folios
    0.72
    bread
    0.70
    rary
    0.70
    ertodd
    0.69
    Activations Density 0.005%

    No Known Activations