© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 3-RES-JB
    6. 13605
    Prev
    Next
    INDEX
    Explanations

    mentions or references to a specific person named Cle**gg**

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Clegg."

    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
    yrinth
    -0.71
    ional
    -0.68
     Helsinki
    -0.67
    uating
    -0.66
    tumblr
    -0.66
    uates
    -0.66
    Interstitial
    -0.64
    hips
    -0.64
    utm
    -0.64
     disparate
    -0.64
    POSITIVE LOGITS
    arest
    1.09
    combe
    0.96
    lean
    0.88
    arer
    0.86
    oqu
    0.82
    ogly
    0.81
    llan
    0.79
    mons
    0.79
    leans
    0.79
    aring
    0.79
    Activations Density 0.009%

    No Known Activations