© 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. 9-RES-JB
    11. 10408
    Prev
    Next
    INDEX
    Explanations

    phrases related to edits or removals

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "Rem" and its variations with different suffixes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    в
    -0.66
     Labrador
    -0.66
    FP
    -0.64
    REF
    -0.63
     Hath
    -0.60
    gerald
    -0.59
    glers
    -0.59
     Typh
    -0.59
    realDonaldTrump
    -0.58
     climate
    -0.58
    POSITIVE LOGITS
    arkable
    1.32
    nants
    1.28
    nant
    1.23
    ovable
    1.18
    oving
    1.16
    aining
    1.11
    ainers
    1.10
    ittance
    1.04
    arks
    1.02
    edia
    1.00
    Activations Density 0.029%

    No Known Activations