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. 20276
    Prev
    Next
    INDEX
    Explanations

    instances of the word "Po" with varying activation levels

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "poison" 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
    owship
    -0.74
    enance
    -0.66
     narrator
    -0.65
    stood
    -0.65
    DERR
    -0.63
    worthiness
    -0.63
     EDITION
    -0.62
    lain
    -0.61
    nah
    -0.61
    UAL
    -0.58
    POSITIVE LOGITS
    ppy
    1.25
    pper
    1.25
    etry
    1.19
    pping
    1.18
    orer
    1.11
    ppel
    1.09
    inters
    1.09
    pped
    1.06
    vernment
    1.06
    achers
    1.06
    Activations Density 0.041%

    No Known Activations