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. 2-RES-JB
    6. 17312
    Prev
    Next
    INDEX
    Explanations

    references to dead or deceased bodies

    oai_token-act-pair · gpt-3.5-turbo

    references to deceased individuals and their remains

    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
     Hoover
    -0.81
     Liberty
    -0.64
     Cobb
    -0.64
     Channel
    -0.64
     Nex
    -0.63
    æ©Ł
    -0.63
     Motorsport
    -0.62
    BILITY
    -0.61
    é¾į
    -0.61
    Americ
    -0.60
    POSITIVE LOGITS
    hops
    1.04
    anguage
    1.00
    matter
    0.94
    chool
    0.93
     bodies
    0.91
    wagen
    0.91
    guards
    0.86
    boro
    0.85
    ynthesis
    0.85
    pots
    0.81
    Activations Density 0.011%

    No Known Activations