© 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. 0-RES-JB
    11. 400
    Prev
    Next
    INDEX
    Explanations

    terms related to the concept of foil, such as preventing or thwarting actions or plans

    oai_token-act-pair · gpt-3.5-turbo

    terms associated with protective barriers or materials

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Wid
    -0.75
    inst
    -0.73
    iny
    -0.68
    ren
    -0.67
     Mass
    -0.66
     Kom
    -0.65
    tn
    -0.64
     Tuc
    -0.64
     Pap
    -0.64
    º
    -0.63
    POSITIVE LOGITS
     foil
    4.27
     fencing
    1.08
     thwart
    1.06
     fo
    1.01
     solder
    1.01
     counterfeit
    1.00
    fo
    0.97
     parchment
    0.97
     cardboard
    0.97
     shielding
    0.95
    Activations Density 0.027%

    No Known Activations