© 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. 0-RES-JB
    11. 6544
    Prev
    Next
    INDEX
    Explanations

    dates in a specific format: Month Day, Year, and numbers potentially representing time like 7:00 or 7:30

    oai_token-act-pair · gpt-3.5-turbo

    specific numerical values or references to a particular number

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ndra
    -0.79
    dyl
    -0.72
    ership
    -0.71
    istry
    -0.68
    utation
    -0.66
    alties
    -0.65
    rency
    -0.63
    Ø©
    -0.59
    TextColor
    -0.58
    tymology
    -0.57
    POSITIVE LOGITS
     7
    2.79
     6
    2.24
     8
    2.21
     9
    2.08
     5
    2.00
     4
    1.78
     11
    1.73
     3
    1.72
     770
    1.71
     13
    1.69
    Activations Density 0.029%

    No Known Activations