© 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. 21137
    Prev
    Next
    INDEX
    Explanations

    references to issues, episodes, volumes, and rounds in published works

    oai_token-act-pair · gpt-3.5-turbo

    references to issues, episodes, or chapters in serialized content

    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
    ibr
    -0.59
     Nobel
    -0.58
    externalActionCode
    -0.56
     Klu
    -0.54
    atro
    -0.52
    ught
    -0.51
    oli
    -0.51
     Sorce
    -0.51
    illard
    -0.50
     Legions
    -0.49
    POSITIVE LOGITS
     TWO
    1.18
     1
    1.18
     2
    1.16
     THREE
    1.13
     3
    1.11
     VIII
    1.08
     4
    1.08
     eleven
    1.07
     6
    1.06
     5
    1.06
    Activations Density 0.252%

    No Known Activations