© 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. 3-RES-JB
    11. 520
    Prev
    Next
    INDEX
    Explanations

    phrases related to support, encouragement, or advancement

    oai_token-act-pair · gpt-3.5-turbo

    key actions or results related to support and development initiatives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    jri
    -0.59
    issan
    -0.57
    arty
    -0.54
    berman
    -0.54
    idav
    -0.52
    essen
    -0.52
    acs
    -0.50
    osures
    -0.50
    braska
    -0.48
    rets
    -0.48
    POSITIVE LOGITS
     preceded
    0.56
     outweigh
    0.52
     resembled
    0.51
    é¾įå¥ij士
    0.50
     happened
    0.50
     ought
    0.50
     coincides
    0.50
     translates
    0.50
    ĨĴ
    0.50
     belonged
    0.49
    Activations Density 2.148%

    No Known Activations