© 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. 12856
    Prev
    Next
    INDEX
    Explanations

    words related to negative or problematic situations or conditions

    oai_token-act-pair · gpt-3.5-turbo

    terms related to negative impacts and ongoing troubles

    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
    uties
    -0.86
    zie
    -0.79
     sidx
    -0.77
    wcsstore
    -0.76
    pmwiki
    -0.74
    quickShipAvailable
    -0.73
    zik
    -0.72
    aru
    -0.71
    ZI
    -0.68
    hao
    -0.68
    POSITIVE LOGITS
     Europe
    1.15
     humankind
    1.03
     humanity
    1.00
     America
    0.99
     mankind
    0.94
     havoc
    0.90
     campuses
    0.90
     society
    0.90
     Britain
    0.89
     our
    0.89
    Activations Density 0.205%

    No Known Activations