Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 24558
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "alk"

    oai_token-act-pair · gpt-3.5-turbo

    references to the term "alk" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Revenue
    -0.74
     jud
    -0.70
     requ
    -0.67
     DOC
    -0.64
     relief
    -0.64
     revenues
    -0.62
     fore
    -0.62
     exercise
    -0.61
     revenue
    -0.61
     Cons
    -0.61
    POSITIVE LOGITS
    alk
    4.55
    ALK
    2.00
    alks
    1.73
    alking
    1.56
    alker
    1.56
    alky
    1.39
    alde
    1.25
    ork
    1.12
    ahl
    1.11
    ech
    1.09
    Activations Density 0.010%

    No Known Activations