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

    Neuronpedia

    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. 20650
    Prev
    Next
    INDEX
    Explanations

    phrases related to importance or significance

    oai_token-act-pair · gpt-3.5-turbo

    the article "an" in various contexts

    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
     dozen
    -0.64
    dylib
    -0.64
    lf
    -0.63
    çĭ
    -0.60
    lyak
    -0.60
    venge
    -0.60
    kai
    -0.59
    mson
    -0.59
    verting
    -0.59
    pert
    -0.58
    POSITIVE LOGITS
     indication
    1.11
     understatement
    1.05
     integral
    1.02
     indicator
    1.01
     anomaly
    1.00
     invitation
    1.00
     extension
    1.00
     impossibility
    0.99
    ointed
    0.99
     exaggeration
    0.99
    Activations Density 0.110%

    No Known Activations