© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 17668
    Prev
    Next
    INDEX
    Explanations

    phrases related to the number "twelve"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "Tw."

    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
    ãĥ£
    -0.76
     association
    -0.63
    tenance
    -0.62
    WARE
    -0.61
     territorial
    -0.60
     prone
    -0.60
     PRESS
    -0.59
     Louie
    -0.58
     Liber
    -0.57
     proprietary
    -0.57
    POSITIVE LOGITS
    elve
    1.67
    elfth
    1.51
    ilight
    1.45
    enty
    1.35
    olves
    1.31
    orld
    1.25
    isted
    1.24
    itters
    1.23
    inkle
    1.22
    irling
    1.18
    Activations Density 0.015%

    No Known Activations