© 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. 9-RES-JB
    11. 7504
    Prev
    Next
    INDEX
    Explanations

    phrases indicating actions or intentions

    oai_token-act-pair · gpt-3.5-turbo

    sentences containing forms of the verb "to be" and related auxiliary verbs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ð
    -0.70
    bush
    -0.70
    hedon
    -0.66
    gom
    -0.65
    Fake
    -0.61
    ente
    -0.60
    conn
    -0.59
    )=(
    -0.58
    uctor
    -0.58
    bury
    -0.57
    POSITIVE LOGITS
     also
    1.43
     furthermore
    1.39
     moreover
    1.34
     therefore
    1.21
     additionally
    1.14
     however
    1.07
    also
    1.06
     meanwhile
    1.02
     then
    0.99
     thus
    0.96
    Activations Density 0.481%

    No Known Activations