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. 6-RES-JB
    6. 22324
    Prev
    Next
    INDEX
    Explanations

    words related to swift and quick actions or movements

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the word "sw" as a prefix or part of a word, indicating some form of movement or action

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ICAL
    -0.72
    OPLE
    -0.70
    Reloaded
    -0.70
     preferential
    -0.70
    _-
    -0.69
     negligent
    -0.68
    pora
    -0.67
    ENSE
    -0.63
    MENTS
    -0.62
     FANT
    -0.61
    POSITIVE LOGITS
    immers
    1.12
    apon
    1.09
    inging
    1.06
    imming
    1.04
    indle
    1.04
    arf
    1.03
    itched
    1.02
    anky
    1.02
    addle
    1.01
    erd
    0.98
    Activations Density 0.010%

    No Known Activations