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. 3-RES-JB
    6. 19440
    Prev
    Next
    INDEX
    Explanations

    words ending in "-ious" or "-ing" that may indicate a more negative or critical tone

    oai_token-act-pair · gpt-3.5-turbo

    words with the suffix '-ous' or related abstract nouns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Rabbit
    -0.53
     Shooter
    -0.50
     Thing
    -0.50
     Hunt
    -0.49
     Gim
    -0.46
    lux
    -0.46
     Det
    -0.45
     Brill
    -0.45
     Beard
    -0.45
     Barrel
    -0.45
    POSITIVE LOGITS
    theless
    0.62
    lly
    0.56
    etheless
    0.56
    terness
    0.55
    quartered
    0.54
     agre
    0.53
     behav
    0.52
    imity
    0.51
    Compat
    0.50
    alon
    0.50
    Activations Density 0.713%

    No Known Activations