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

    Neuronpedia

    Jacobian LensNEW
    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. 10-RES-JB
    11. 3007
    Prev
    Next
    INDEX
    Explanations

    phrases related to specific activities or events happening at a certain time of day

    oai_token-act-pair · gpt-3.5-turbo

    descriptions of daily activities and routines

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Accountability
    -0.66
     math
    -0.65
     DEFENSE
    -0.63
    Correction
    -0.60
     SNAP
    -0.59
     Accounting
    -0.58
     defense
    -0.58
     MORE
    -0.57
     AMERICA
    -0.57
     DOE
    -0.56
    POSITIVE LOGITS
     favoured
    0.98
     colourful
    0.97
     emphas
    0.97
     organisers
    0.95
    usually
    0.93
     organised
    0.92
     invariably
    0.91
     behaviours
    0.84
     neighbours
    0.83
     manoeuv
    0.80
    Activations Density 1.059%

    No Known Activations