© 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 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. 11-RES-JB
    11. 14917
    Prev
    Next
    INDEX
    Explanations

    file-related actions or operations

    oai_token-act-pair · gpt-3.5-turbo

    conditional statements and the presence of the verb "is"

    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
    DragonMagazine
    -0.84
     Pledge
    -0.75
     refunds
    -0.71
    ookie
    -0.67
    details
    -0.66
    Topics
    -0.66
    Guide
    -0.66
    ERAL
    -0.65
    Scroll
    -0.64
     pains
    -0.63
    POSITIVE LOGITS
     detected
    1.01
     unavailable
    0.98
     already
    0.96
     located
    0.94
     configured
    0.94
     occupied
    0.93
     placed
    0.91
     paired
    0.90
     not
    0.89
     present
    0.89
    Activations Density 0.189%

    No Known Activations