© 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. 10-RES-JB
    11. 8524
    Prev
    Next
    INDEX
    Explanations

    names containing the string "ick"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the substring "ick" in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ILCS
    -0.72
    ãĥ´ãĤ¡
    -0.66
    ãĤ£
    -0.66
    EMBER
    -0.65
    oding
    -0.65
    ãģ®å
    -0.64
    PsyNetMessage
    -0.64
    ctic
    -0.63
     lingu
    -0.61
    orescence
    -0.60
    POSITIVE LOGITS
    leness
    1.20
    ety
    1.14
    ering
    1.13
    ett
    1.13
    erman
    1.13
    ery
    1.08
    hoff
    1.01
    eters
    1.00
    lers
    0.98
    eter
    0.98
    Activations Density 0.052%

    No Known Activations