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. 8-RES-JB
    6. 5997
    Prev
    Next
    INDEX
    Explanations

    phrases related to the Islamic State in Iraq and Syria (ISIS)

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "and" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tone
    -0.77
    piece
    -0.71
    Publisher
    -0.70
    sth
    -0.68
    hiba
    -0.66
    actionDate
    -0.65
    onomic
    -0.65
    ommel
    -0.65
    oret
    -0.64
    mega
    -0.62
    POSITIVE LOGITS
    romeda
    0.86
    EStream
    0.76
     Caucasus
    0.71
     Herz
    0.71
     Puerto
    0.69
     Wales
    0.67
     Labrador
    0.67
     Levant
    0.67
    Nev
    0.66
    ghazi
    0.65
    Activations Density 0.099%

    No Known Activations