© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 12-RES-JB
    11. 3863
    Prev
    Next
    INDEX
    Explanations

    actions or events with a strong impact or result

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    instances of the word "off" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    zan
    -0.52
    Cola
    -0.51
    quer
    -0.50
    elta
    -0.48
    sie
    -0.47
    qqa
    -0.47
    abad
    -0.46
    ŃĶ
    -0.46
    verbs
    -0.46
    zie
    -0.45
    POSITIVE LOGITS
     of
    1.58
    of
    1.33
     Of
    1.27
    Of
    1.25
     thereof
    1.20
     OF
    1.15
    OF
    0.85
    oft
    0.80
    luster
    0.53
    eatures
    0.51
    Activations Density 1.213%

    No Known Activations