© 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. 10569
    Prev
    Next
    INDEX
    Explanations

    words related to starting or undertaking a new action or adventure

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to embarking on journeys or ventures

    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
    verbs
    -0.78
    gnu
    -0.64
     circumst
    -0.63
    creen
    -0.62
    pert
    -0.60
     overhead
    -0.58
    ollah
    -0.58
     cue
    -0.57
    naissance
    -0.57
    gio
    -0.57
    POSITIVE LOGITS
    ãĥĦ
    0.97
    TAIN
    0.93
    ãĤ¼ãĤ¦ãĤ¹
    0.88
     embark
    0.84
     embarked
    0.82
    edIn
    0.82
    ãĥ¼ãĥĨãĤ£
    0.80
    ãĥĢ
    0.75
    alis
    0.75
    ãĥī
    0.73
    Activations Density 0.009%

    No Known Activations