© 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. 0-RES-JB
    11. 15728
    Prev
    Next
    INDEX
    Explanations

    words related to spatial or temporal movement

    oai_token-act-pair · gpt-3.5-turbo

    references to the word "back" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    inite
    -0.80
    lime
    -0.75
    urated
    -0.72
    cientious
    -0.67
    ICH
    -0.65
     Causes
    -0.64
     Ideal
    -0.62
    adish
    -0.62
    icia
    -0.62
    pract
    -0.60
    POSITIVE LOGITS
     back
    3.22
     backs
    2.33
     BACK
    2.26
    back
    2.25
     Back
    2.21
    Back
    2.07
    backs
    1.87
    BACK
    1.73
     backend
    1.24
     backwards
    1.19
    Activations Density 0.067%

    No Known Activations