© 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. 23038
    Prev
    Next
    INDEX
    Explanations

    words associated with separation or division

    oai_token-act-pair · gpt-3.5-turbo

    the presence of the word "se."

    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
    rolet
    -0.80
    é¾įå
    -0.77
    raviolet
    -0.74
    sonian
    -0.70
    enhagen
    -0.70
     CPC
    -0.68
     hoops
    -0.67
    kson
    -0.65
    culosis
    -0.65
    orsi
    -0.65
    POSITIVE LOGITS
    vel
    0.95
    perate
    0.93
    leanor
    0.89
    clusion
    0.88
    rend
    0.85
    eps
    0.85
    arest
    0.83
    wed
    0.82
    ls
    0.82
    gment
    0.82
    Activations Density 0.007%

    No Known Activations