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. 18241
    Prev
    Next
    INDEX
    Explanations

    phrases related to comparison or assessment

    oai_token-act-pair · gpt-3.5-turbo

    simple present and past tense forms of the verb "to be."

    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
    idth
    -0.73
    ilst
    -0.70
    alth
    -0.68
    ESE
    -0.66
    iasco
    -0.65
    these
    -0.63
    ievers
    -0.62
    uese
    -0.62
    wake
    -0.61
    atures
    -0.61
    POSITIVE LOGITS
    ometric
    0.74
     priceless
    0.72
     preferable
    0.71
     downright
    0.69
     presumed
    0.69
    olation
    0.69
    trak
    0.68
    omorphic
    0.68
     unmist
    0.67
     merely
    0.67
    Activations Density 0.288%

    No Known Activations