© 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. 21168
    Prev
    Next
    INDEX
    Explanations

    copyright statements and years

    oai_token-act-pair · gpt-3.5-turbo

    copyright years and related legal terms

    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
    ment
    -0.68
    enance
    -0.67
     upside
    -0.65
    awed
    -0.64
    ificant
    -0.63
    rine
    -0.60
    viation
    -0.59
    orno
    -0.59
    orer
    -0.59
     pockets
    -0.57
    POSITIVE LOGITS
     Globe
    0.86
     Creat
    0.84
     KING
    0.79
     Nex
    0.79
     Tribune
    0.78
     NPR
    0.76
    taboola
    0.76
     Cosponsors
    0.75
     Hawaii
    0.74
     WCS
    0.74
    Activations Density 0.028%

    No Known Activations