© 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. 3524
    Prev
    Next
    INDEX
    Explanations

    phrases related to taking action or responding to a situation

    oai_token-act-pair · gpt-3.5-turbo

    negations or phrases expressing refusal or denial

    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
    akedown
    -0.74
    ailability
    -0.72
    bda
    -0.64
    lishes
    -0.63
    retty
    -0.63
    ongevity
    -0.61
    pend
    -0.58
    natureconservancy
    -0.58
    uncture
    -0.56
    ravel
    -0.55
    POSITIVE LOGITS
     to
    1.29
     unto
    1.15
     aloud
    1.11
    to
    1.04
     verbally
    1.01
     TO
    0.94
     thereto
    0.90
     anonymously
    0.89
     publicly
    0.88
     towards
    0.88
    Activations Density 0.375%

    No Known Activations