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

    Neuronpedia

    Jacobian LensNEW
    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. 14767
    Prev
    Next
    INDEX
    Explanations

    proper names, particularly with the string "rew" in them

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "rew" and its derivatives

    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
    ãĥīãĥ©ãĤ´ãĥ³
    -0.77
     Ghana
    -0.76
     è£ı
    -0.73
     è£ıè¦ļéĨĴ
    -0.68
     Kenyan
    -0.68
     Senegal
    -0.68
     Cameroon
    -0.65
     Liberia
    -0.64
     Nigerian
    -0.63
     AUTH
    -0.63
    POSITIVE LOGITS
    ritten
    0.99
    rew
    0.97
    atts
    0.90
    atche
    0.89
    esley
    0.88
    driver
    0.88
    ards
    0.88
    atcher
    0.88
    ipes
    0.87
    icz
    0.86
    Activations Density 0.003%

    No Known Activations