© 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. 14514
    Prev
    Next
    INDEX
    Explanations

    specific organization names

    oai_token-act-pair · gpt-3.5-turbo

    references to organizations, institutions, or places

    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
     pedals
    -0.87
     tremend
    -0.84
     destro
    -0.84
     blasp
    -0.82
     tyr
    -0.82
     gobl
    -0.80
     confir
    -0.80
     notor
    -0.78
     flavours
    -0.75
     describ
    -0.75
    POSITIVE LOGITS
     Community
    1.27
     Intermediate
    1.26
     Regional
    1.24
     Improvement
    1.21
     Municipal
    1.20
     Cooperative
    1.18
     Compact
    1.18
     Educational
    1.17
     Retirement
    1.16
     Independent
    1.15
    Activations Density 0.394%

    No Known Activations