© 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. 11-RES-JB
    11. 22417
    Prev
    Next
    INDEX
    Explanations

    phrases indicating cause and effect

    oai_token-act-pair · gpt-3.5-turbo

    the word "as" used in various contexts conveying comparison or effect

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     whatsoever
    -0.69
    origin
    -0.61
    âĻ¦
    -0.61
    atis
    -0.60
    gger
    -0.57
    leans
    -0.56
    opian
    -0.56
    abouts
    -0.56
    regon
    -0.55
    ALLY
    -0.55
    POSITIVE LOGITS
    pects
    1.16
    ymm
    1.16
    semb
    1.13
    piring
    1.08
    ynchronous
    1.06
    bestos
    1.05
    phalt
    1.01
    piration
    0.99
     such
    0.95
    semble
    0.95
    Activations Density 0.077%

    No Known Activations