© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 10-RES-JB
    11. 12796
    Prev
    Next
    INDEX
    Explanations

    adverbs indicating degree or intensity

    oai_token-act-pair · gpt-3.5-turbo

    qualifiers indicating moderate to strong degrees of sentiment or description

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ULTS
    -1.08
    ulkan
    -0.88
    ividual
    -0.87
    ults
    -0.85
    idth
    -0.84
    abad
    -0.83
    INESS
    -0.83
    mson
    -0.83
    onis
    -0.82
    atches
    -0.82
    POSITIVE LOGITS
     amusing
    1.14
     unrem
    1.14
     unorthodox
    1.12
     disappointing
    1.10
     unconventional
    1.10
     cryptic
    1.09
     bland
    1.07
     surprising
    1.06
     unusual
    1.06
     pathetic
    1.05
    Activations Density 0.078%

    No Known Activations