© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 12-RES-JB
    6. 3034
    Prev
    Next
    INDEX
    Explanations

    numerical values or quantities associated with economics or technical details

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

    phrases related to timing and synchronization

    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
    ãĥĻ
    -0.68
    inav
    -0.67
    warn
    -0.66
    uphem
    -0.66
    licts
    -0.66
    suits
    -0.66
    packages
    -0.65
    brids
    -0.65
    ieties
    -0.64
    ploma
    -0.64
    POSITIVE LOGITS
     time
    1.45
     moment
    1.39
     point
    1.37
     location
    1.35
     place
    1.16
     spot
    1.15
     stage
    1.14
     pace
    1.11
     date
    1.11
     jun
    1.11
    Activations Density 0.147%

    No Known Activations