© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 23993
    Prev
    Next
    INDEX
    Explanations

    words related to technology and coding, specifically detecting mentions of the coding language 'sle'

    oai_token-act-pair · gpt-3.5-turbo

    instances of the empty token or significant breaks in the text structure

    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
    onomy
    -0.72
     sqor
    -0.67
    interrupted
    -0.64
    sic
    -0.59
    nas
    -0.58
    idia
    -0.58
     Honor
    -0.58
    IFIED
    -0.56
    shire
    -0.55
    iously
    -0.55
    POSITIVE LOGITS
    cks
    1.18
    eker
    1.10
    aping
    1.08
    eper
    1.08
    ³
    1.03
    aker
    1.02
    ppers
    1.01
    aves
    1.01
    pped
    1.01
    ppings
    1.00
    Activations Density 0.208%

    No Known Activations