Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 12175
    Prev
    Next
    INDEX
    Explanations

    words signaling contrast or contradiction in a sentence

    oai_token-act-pair · gpt-3.5-turbo

    expressions of hope and concern about future actions or events

    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
    eer
    -0.60
     guiActiveUnfocused
    -0.59
    ãĥ´
    -0.57
    atro
    -0.55
    Joined
    -0.55
    Offline
    -0.54
    arthed
    -0.54
    CAN
    -0.54
    Translation
    -0.53
    arching
    -0.53
    POSITIVE LOGITS
     however
    2.36
     though
    1.83
     meanwhile
    1.58
     moreover
    1.37
     tho
    1.35
     therefore
    1.34
     furthermore
    1.06
    However
    0.85
     likewise
    0.84
    Nonetheless
    0.84
    Activations Density 1.638%

    No Known Activations