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. 16873
    Prev
    Next
    INDEX
    Explanations

    phrases or sentences containing the word "cheer" in various forms or contexts

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "cheer" and related forms, indicating enthusiasm or support

    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
    nesota
    -0.72
    ahime
    -0.71
    enture
    -0.66
    artment
    -0.63
    entially
    -0.63
    copy
    -0.62
     Explorer
    -0.61
     Danger
    -0.61
     encyclopedia
    -0.60
     monastery
    -0.60
    POSITIVE LOGITS
    leaders
    1.49
    leading
    1.45
    leader
    1.42
    lead
    1.22
     cheering
    1.03
     louder
    1.00
     cheer
    0.97
    hovah
    0.95
     loudly
    0.95
    fulness
    0.94
    Activations Density 0.056%

    No Known Activations