© 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. 17906
    Prev
    Next
    INDEX
    Explanations

    verbs in the past tense followed by a time reference

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "After" followed by a number, indicating sequences or events

    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
     species
    -0.63
     lever
    -0.62
     fault
    -0.61
     mean
    -0.61
     breed
    -0.59
     contempt
    -0.59
     represented
    -0.59
    pell
    -0.59
     biological
    -0.59
     rank
    -0.59
    POSITIVE LOGITS
     After
    2.85
    After
    2.17
     Afterwards
    2.12
     Following
    2.03
     During
    1.82
     Before
    1.78
    after
    1.72
     AFTER
    1.68
     Later
    1.68
     Upon
    1.65
    Activations Density 0.020%

    No Known Activations