Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 9183
    Prev
    Next
    INDEX
    Explanations

    hyperlinks or social media buttons

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "Like" often in relation to social media engagement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Ö¼
    -0.66
     intermedi
    -0.60
    uliffe
    -0.57
     extracted
    -0.56
    arthy
    -0.56
    illin
    -0.56
     enthusi
    -0.55
    ENE
    -0.55
    endiary
    -0.54
    rang
    -0.54
    POSITIVE LOGITS
    lihood
    1.78
    liest
    1.11
    minded
    1.04
    liness
    1.03
     minded
    1.01
    ability
    0.88
    lier
    0.87
     Loading
    0.87
     Us
    0.82
     Clockwork
    0.81
    Activations Density 0.036%

    No Known Activations