© 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. 2283
    Prev
    Next
    INDEX
    Explanations

    phrases related to early time periods or events

    oai_token-act-pair · gpt-3.5-turbo

    references to the word "early."

    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
    rael
    -0.64
    dict
    -0.64
    alist
    -0.64
    lette
    -0.63
     Column
    -0.61
    SPONSORED
    -0.60
    wick
    -0.60
    eree
    -0.59
    ILA
    -0.59
    ocide
    -0.59
    POSITIVE LOGITS
     early
    3.39
    Early
    2.38
     late
    2.35
     Early
    2.28
    early
    2.02
     earliest
    2.01
     earlier
    1.60
     mid
    1.57
    Late
    1.55
     Late
    1.47
    Activations Density 0.033%

    No Known Activations