© 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. 2-RES-JB
    11. 17305
    Prev
    Next
    INDEX
    Explanations

    phrases that contain the letter "c" followed by a digit ranging from 9 to 10

    oai_token-act-pair · gpt-3.5-turbo

    the character 'c' in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ĪĴ
    -0.85
    EStream
    -0.83
     explan
    -0.73
     Tinder
    -0.67
     Maker
    -0.66
     GOODMAN
    -0.65
     Grateful
    -0.65
     juggling
    -0.64
    ãĥĹ
    -0.63
     contagious
    -0.63
    POSITIVE LOGITS
    ursor
    1.22
    ancel
    1.12
    ologne
    1.12
    oding
    1.10
    rawl
    1.10
    otton
    1.09
    oder
    1.08
    ursed
    1.07
    isco
    1.06
    ounters
    1.06
    Activations Density 0.034%

    No Known Activations