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. 21743
    Prev
    Next
    INDEX
    Explanations

    adverbs or adjectives ending in 'ingly', 'ably', or 'ously'

    oai_token-act-pair · gpt-3.5-turbo

    adverbs that convey strong emotional or physical states

    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
    orem
    -0.78
    icipated
    -0.76
    speech
    -0.74
    icip
    -0.72
    elsen
    -0.70
    rite
    -0.69
    Sah
    -0.68
    ordan
    -0.68
    rike
    -0.68
    rows
    -0.67
    POSITIVE LOGITS
     inaccurate
    0.84
     accurate
    0.84
     timed
    0.81
     inept
    0.81
     underrated
    0.81
     close
    0.80
     inefficient
    0.78
     cheap
    0.78
     catchy
    0.77
     situated
    0.76
    Activations Density 0.099%

    No Known Activations