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. 21934
    Prev
    Next
    INDEX
    Explanations

    phrases that describe something as distinct, exceptional, or one-of-a-kind

    oai_token-act-pair · gpt-3.5-turbo

    phrases describing uniqueness or distinctiveness

    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
    Continue
    -0.62
    wash
    -0.61
     Instr
    -0.61
     residues
    -0.60
     tighten
    -0.60
     fumes
    -0.59
    aintain
    -0.59
     buildup
    -0.58
     misinformation
    -0.56
    Loading
    -0.56
    POSITIVE LOGITS
     uniqueness
    1.06
    iqueness
    0.86
     unique
    0.83
     pecul
    0.82
     exception
    0.78
     rarity
    0.76
     uniquely
    0.75
     exceptional
    0.75
     distinguishes
    0.73
     circumstance
    0.73
    Activations Density 0.409%

    No Known Activations