© 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. 4-RES-JB
    11. 22620
    Prev
    Next
    INDEX
    Explanations

    keywords related to outcomes or results

    oai_token-act-pair · gpt-3.5-turbo

    the term "resulting" and its variations, indicating outcomes or effects

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

    No Comments

    Negative Logits
    fing
    -0.80
    bor
    -0.73
    trak
    -0.72
    stra
    -0.68
    ifications
    -0.67
    cellence
    -0.65
    pell
    -0.63
    untu
    -0.63
    pelling
    -0.62
    thinkable
    -0.62
    POSITIVE LOGITS
    INAL
    0.81
    ames
    0.77
    ãĤº
    0.76
    uces
    0.75
    ãĤ¦ãĤ¹
    0.74
    uced
    0.73
    AMES
    0.73
    >(
    0.72
    ãĤ¼ãĤ¦ãĤ¹
    0.71
    aneous
    0.70
    Activations Density 0.014%

    No Known Activations