© 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. 18642
    Prev
    Next
    INDEX
    Explanations

    the letter 'k' occurring in combination with other adjacent letters

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the letter "k"

    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
     gallon
    -0.65
     Shelby
    -0.62
     Bowling
    -0.61
     diarrhea
    -0.60
     Bloom
    -0.58
     TTL
    -0.58
     friction
    -0.57
     missionary
    -0.57
    BIP
    -0.57
     cross
    -0.56
    POSITIVE LOGITS
    omm
    1.29
    lein
    1.17
    riminal
    1.17
    ulture
    1.16
    redit
    1.16
    rieg
    1.15
    ompl
    1.14
    ult
    1.11
    lass
    1.11
    ont
    1.11
    Activations Density 0.051%

    No Known Activations