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. 14157
    Prev
    Next
    INDEX
    Explanations

    prepositional phrases starting with "from which"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "which," indicating a focus on relative clauses or phrases that provide additional information

    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
     WATCHED
    -0.72
     Panda
    -0.69
    swick
    -0.67
    Sty
    -0.66
     Ll
    -0.66
    DIT
    -0.66
    grim
    -0.63
    Bug
    -0.62
    zilla
    -0.61
    Cent
    -0.61
    POSITIVE LOGITS
    soever
    1.03
    xual
    0.85
    izens
    0.79
    ipple
    0.71
     defenses
    0.68
     sust
    0.64
     dearly
    0.64
    isson
    0.64
     thous
    0.63
    izen
    0.62
    Activations Density 0.032%

    No Known Activations