© 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. 10-RES-JB
    11. 15997
    Prev
    Next
    INDEX
    Explanations

    verbs indicating future actions or possibilities

    oai_token-act-pair · gpt-3.5-turbo

    modal verbs indicating uncertainty or possibility

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     adolesc
    -0.60
     Citiz
    -0.57
     pione
    -0.56
     metic
    -0.56
    WithNo
    -0.56
    olini
    -0.54
     newcomer
    -0.53
    ãĤ¶
    -0.52
     corrid
    -0.51
    asus
    -0.51
    POSITIVE LOGITS
    .
    1.41
    !.
    1.32
    !
    1.31
    .[
    1.21
    .(
    1.20
    ;
    1.20
     ;)
    1.18
     :)
    1.16
    !!!!
    1.15
    .--
    1.15
    Activations Density 0.427%

    No Known Activations