© 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. 4-RES-JB
    6. 19501
    Prev
    Next
    INDEX
    Explanations

    mentions of obituaries

    oai_token-act-pair · gpt-3.5-turbo

    the word "it" in various contexts

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

    No Comments

    Negative Logits
    ©¶æ
    -0.94
     resil
    -0.78
     therap
    -0.71
    £ı
    -0.70
     destro
    -0.70
     pudding
    -0.69
    pter
    -0.69
     dams
    -0.69
    dayName
    -0.65
     GEAR
    -0.62
    POSITIVE LOGITS
    uary
    0.99
    ocracy
    0.93
    chell
    0.92
    ariat
    0.88
    amins
    0.87
    TY
    0.84
    hew
    0.84
    illary
    0.84
    aires
    0.83
    folios
    0.80
    Activations Density 0.020%

    No Known Activations