© 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. 7-RES-JB
    6. 2951
    Prev
    Next
    INDEX
    Explanations

    the word "shy" or variations of it within the text

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "shy" and its variations in context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    è¦ļéĨĴ
    -0.85
    akeru
    -0.75
    ghazi
    -0.70
    ichick
    -0.70
     surv
    -0.64
    ACTED
    -0.62
    女
    -0.61
     Maher
    -0.60
    代
    -0.60
     Uz
    -0.59
    POSITIVE LOGITS
    ness
    1.35
    vana
    1.27
    ety
    1.06
    nesses
    1.03
    lish
    1.03
    sters
    0.99
    ly
    0.96
    ster
    0.93
    ening
    0.91
    est
    0.85
    Activations Density 0.021%

    No Known Activations