© 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. 3-RES-JB
    11. 22861
    Prev
    Next
    INDEX
    Explanations

    terms related to long-term planning or considerations

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to long-term considerations and planning

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Cosponsors
    -1.16
    chy
    -0.93
    hou
    -0.92
    IDES
    -0.90
    HOU
    -0.90
     Klu
    -0.79
    bats
    -0.77
    lez
    -0.75
    ching
    -0.75
    gyn
    -0.72
    POSITIVE LOGITS
     viability
    0.91
     sustainability
    0.87
     unemployed
    0.85
     survival
    0.83
     outcomes
    0.81
     durability
    0.81
     outcome
    0.80
    term
    0.80
     usefulness
    0.80
     stability
    0.78
    Activations Density 0.016%

    No Known Activations