© 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. 0-RES-JB
    11. 12077
    Prev
    Next
    INDEX
    Explanations

    phrases related to taking action or making decisions

    oai_token-act-pair · gpt-3.5-turbo

    the infinitive form of verbs, specifically "to" followed by another verb

    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
    midt
    -0.63
    etheless
    -0.61
    theless
    -0.55
    aah
    -0.51
    unct
    -0.51
    mosp
    -0.49
    jamin
    -0.49
    deen
    -0.48
    osi
    -0.48
    leneck
    -0.47
    POSITIVE LOGITS
     to
    1.76
     thereto
    1.18
    to
    1.07
     unto
    0.97
     TO
    0.91
    To
    0.91
     towards
    0.88
     toward
    0.86
     To
    0.86
     onto
    0.77
    Activations Density 1.370%

    No Known Activations