© 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. 17283
    Prev
    Next
    INDEX
    Explanations

    keywords related to directives or suggestions

    oai_token-act-pair · gpt-3.5-turbo

    action-oriented verbs related to suggestions, acceptance, and collection

    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
    ctica
    -0.74
     deaf
    -0.70
    USE
    -0.70
    Downloadha
    -0.70
    ULTS
    -0.66
     crawl
    -0.65
    apter
    -0.65
    avorite
    -0.65
     nap
    -0.62
     pleasure
    -0.60
    POSITIVE LOGITS
    ed
    1.92
    ing
    1.74
    edIn
    1.31
    edly
    1.26
    ership
    1.14
    edin
    1.09
    ers
    1.05
    s
    1.05
    ington
    1.03
    er
    1.02
    Activations Density 0.135%

    No Known Activations