© 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. 8-RES-JB
    11. 6062
    Prev
    Next
    INDEX
    Explanations

    the term "Us" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    words related to media or news outlets

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     confinement
    -0.68
     runoff
    -0.64
     gloss
    -0.61
     combustion
    -0.61
     plateau
    -0.60
     plaque
    -0.59
     meth
    -0.58
     poaching
    -0.57
     concentrating
    -0.57
     skirt
    -0.56
    POSITIVE LOGITS
    hers
    1.26
    agi
    1.15
    ername
    1.12
    ual
    1.05
    earchers
    1.03
    ages
    1.03
    chwitz
    1.03
    urers
    1.00
    ern
    0.96
    atisf
    0.96
    Activations Density 0.031%

    No Known Activations