© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 11-RES-JB
    6. 4225
    Prev
    Next
    INDEX
    Explanations

    words related to hindering, harming, or impeding something

    oai_token-act-pair · gpt-3.5-turbo

    negative or harmful impacts on various subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     helicop
    -0.72
     Rated
    -0.67
     Oz
    -0.66
     boldly
    -0.65
     reluct
    -0.65
     boxed
    -0.64
     proudly
    -0.64
     prow
    -0.62
     condolences
    -0.60
     brill
    -0.60
    POSITIVE LOGITS
    uce
    0.85
    incent
    0.85
    shed
    0.83
    lace
    0.82
    activate
    0.81
    gage
    0.80
    hibit
    0.79
    oldown
    0.76
    set
    0.75
    mage
    0.75
    Activations Density 0.089%

    No Known Activations