© 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. 1-RES-JB
    11. 14228
    Prev
    Next
    INDEX
    Explanations

    technical terms related to planning and organization

    oai_token-act-pair · gpt-3.5-turbo

    terms related to planning and strategy, particularly in a scheming context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    vation
    -0.78
    ctuary
    -0.72
    ipop
    -0.70
     Clancy
    -0.70
    ocaust
    -0.69
     Violence
    -0.68
    ose
    -0.68
     perjury
    -0.68
    osate
    -0.67
     Chamberlain
    -0.65
    POSITIVE LOGITS
     sche
    1.20
     blueprint
    0.92
    rawn
    0.89
    ses
    0.85
    SpaceEngineers
    0.84
     schematic
    0.84
     specifications
    0.77
    ahime
    0.77
    sburg
    0.77
    iets
    0.77
    Activations Density 0.012%

    No Known Activations