© 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. 11-RES-JB
    11. 11588
    Prev
    Next
    INDEX
    Explanations

    strong verbs indicating action or change

    oai_token-act-pair · gpt-3.5-turbo

    instances of personal transformation and impactful experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    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
    ©¶æ¥µ
    -0.87
    ãĤ¢ãĥ«
    -0.71
     proport
    -0.64
    £ı
    -0.64
    å°Ĩ
    -0.64
    osher
    -0.63
    kees
    -0.62
    ItemTracker
    -0.61
    hower
    -0.61
    è£ħ
    -0.61
    POSITIVE LOGITS
     me
    2.69
     my
    1.83
     mine
    1.56
     myself
    1.46
     ME
    1.44
     MY
    1.31
     us
    1.29
     Me
    1.20
    my
    1.18
    me
    1.16
    Activations Density 0.736%

    No Known Activations