© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 2-RES-JB
    11. 3056
    Prev
    Next
    INDEX
    Explanations

    terms related to strategic planning, specifically focusing on reducing costs, implementing actions, and addressing social issues

    oai_token-act-pair · gpt-3.5-turbo

    various approaches to problem-solving

    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
    rip
    -0.76
    BILITY
    -0.72
     Brotherhood
    -0.70
     IDF
    -0.67
    ded
    -0.66
    ×Ķ
    -0.64
    lich
    -0.61
    onement
    -0.61
    ned
    -0.60
     scratch
    -0.60
    POSITIVE LOGITS
    poons
    1.28
    ettings
    1.23
    uggest
    1.22
    hops
    1.20
    etter
    1.16
    afety
    1.15
    hips
    1.14
    omething
    1.14
    everal
    1.07
    cape
    1.07
    Activations Density 0.137%

    No Known Activations