© 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. 15023
    Prev
    Next
    INDEX
    Explanations

    phrases describing the act of gathering or figuring things out through observations or experiences

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating subjective conclusions or interpretations derived from personal experience

    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
     Lover
    -0.63
     goodbye
    -0.60
     Screw
    -0.60
     understatement
    -0.60
     shame
    -0.59
    bent
    -0.58
     Tight
    -0.58
    adem
    -0.57
    btn
    -0.57
    ospons
    -0.56
    POSITIVE LOGITS
     glean
    1.16
     anecd
    1.07
     heard
    1.06
     hears
    1.02
     gather
    0.99
     hear
    0.98
    heard
    0.97
     gathered
    0.94
     understand
    0.93
     learnt
    0.91
    Activations Density 0.081%

    No Known Activations