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. 23996
    Prev
    Next
    INDEX
    Explanations

    adjectives and nouns that are commonly associated with the verb "tend."

    oai_token-act-pair · gpt-3.5-turbo

    phrases that describe habitual or typical behaviors

    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
    istry
    -0.71
    360
    -0.68
    ceivable
    -0.66
    authent
    -0.62
    Mic
    -0.61
    Buzz
    -0.59
    step
    -0.59
    Inside
    -0.59
    DOWN
    -0.58
    MAP
    -0.58
    POSITIVE LOGITS
     tend
    3.40
     tended
    2.25
     tends
    1.92
     Tend
    1.46
     tending
    1.37
     tendon
    1.21
     usually
    1.17
     skew
    1.13
    pmwiki
    1.13
     typically
    1.11
    Activations Density 0.017%

    No Known Activations