© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 14931
    Prev
    Next
    INDEX
    Explanations

    adjectives and verbs related to reflective surfaces

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of a mirror

    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
    urg
    -0.74
    quit
    -0.73
    acre
    -0.66
     acres
    -0.65
    emp
    -0.65
    sett
    -0.64
    oÄŁ
    -0.64
     Agric
    -0.64
    iety
    -0.63
    unsigned
    -0.63
    POSITIVE LOGITS
     mirror
    4.07
     mirrors
    3.07
     Mirror
    2.20
     mirrored
    2.11
    mir
    1.63
    Mir
    1.47
     reflect
    1.28
     prism
    1.25
     reflective
    1.16
     reflection
    1.13
    Activations Density 0.012%

    No Known Activations