© 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. 4-RES-JB
    11. 18364
    Prev
    Next
    INDEX
    Explanations

    terms related to long-term planning or investment

    oai_token-act-pair · gpt-3.5-turbo

    references to long-term plans or commitment

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

    No Comments

    Negative Logits
     Cosponsors
    -1.01
    HOU
    -0.92
    chy
    -0.89
     DRAG
    -0.87
    hou
    -0.87
    IDES
    -0.83
     Klu
    -0.79
    xtap
    -0.76
    chu
    -0.73
     Coul
    -0.72
    POSITIVE LOGITS
     viability
    0.99
     sustainability
    0.88
    term
    0.84
     survival
    0.83
     stability
    0.81
     unemployed
    0.81
     usefulness
    0.81
    izons
    0.80
     outcomes
    0.80
     retention
    0.79
    Activations Density 0.014%

    No Known Activations