© 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. 8-RES-JB
    11. 7803
    Prev
    Next
    INDEX
    Explanations

    infinitive verbs followed by specific activities or goals

    oai_token-act-pair · gpt-3.5-turbo

    instances of the phrase "to" followed by a verb, indicating intentions or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Child
    -0.63
    Mur
    -0.61
    LAN
    -0.60
    UR
    -0.60
     versus
    -0.59
    iHUD
    -0.59
    skinned
    -0.59
     Mehran
    -0.58
    ··
    -0.58
    SourceFile
    -0.58
    POSITIVE LOGITS
     demonstrate
    1.18
     educate
    1.16
     enhance
    1.14
     facilitate
    1.13
     compensate
    1.12
     minimize
    1.11
     provide
    1.11
     celebrate
    1.10
     satisfy
    1.10
     ensure
    1.10
    Activations Density 0.098%

    No Known Activations