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. 9-RES-JB
    6. 15083
    Prev
    Next
    INDEX
    Explanations

    the verb "to be" followed by another verb, possibly indicating willingness or action

    oai_token-act-pair · gpt-3.5-turbo

    the use of the verb "be" in various grammatical forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Source
    -0.63
    idas
    -0.62
    vertisements
    -0.59
     amplification
    -0.57
    arming
    -0.56
     Aram
    -0.55
    imum
    -0.55
    orius
    -0.55
     propagation
    -0.55
     Indies
    -0.54
    POSITIVE LOGITS
    ngth
    0.79
     thee
    0.78
     somew
    0.75
     plenty
    0.75
     someday
    0.71
     glad
    0.70
    avis
    0.68
     JUSTICE
    0.68
     somet
    0.67
    some
    0.66
    Activations Density 0.122%

    No Known Activations