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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 6334
    Prev
    Next
    INDEX
    Explanations

    dates expressed in simple forms

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the term "greens" and related variations

    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
     sarc
    -0.72
     belt
    -0.69
     accident
    -0.65
     bust
    -0.64
     Sherlock
    -0.64
     Anat
    -0.63
     class
    -0.62
     act
    -0.59
     historical
    -0.59
     Dom
    -0.59
    POSITIVE LOGITS
    reens
    4.65
    reen
    1.69
     Greens
    1.42
    reenshots
    1.21
     greens
    1.19
    owers
    1.06
    ttes
    1.06
    roups
    1.03
    rists
    1.02
    anners
    1.01
    Activations Density 0.012%

    No Known Activations