© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 1-RES-JB
    11. 5167
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "backs"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "backs" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    inct
    -0.78
    inational
    -0.74
    ifix
    -0.67
    icity
    -0.65
    istically
    -0.64
    tein
    -0.64
    isite
    -0.64
    iken
    -0.61
    enture
    -0.60
    ciation
    -0.60
    POSITIVE LOGITS
    lash
    1.13
     backs
    1.01
    uggest
    1.00
    ports
    0.86
    back
    0.86
    backs
    0.84
    pring
    0.81
    packs
    0.77
    side
    0.75
    interstitial
    0.75
    Activations Density 0.005%

    No Known Activations