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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 7-RES-JB
    11. 2011
    Prev
    Next
    INDEX
    Explanations

    mentions of public figures in the context of a public event or statement

    oai_token-act-pair · gpt-3.5-turbo

    mentions of Donald Trump and political events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    qus
    -0.72
    oya
    -0.71
    ãĤ´ãĥ³
    -0.68
    AB
    -0.67
    alo
    -0.67
    irms
    -0.64
    TeX
    -0.64
    isSpecialOrderable
    -0.64
    enta
    -0.64
    SI
    -0.64
    POSITIVE LOGITS
     however
    0.90
     meanwhile
    0.80
     rumors
    0.66
     Giul
    0.64
     detectives
    0.62
     there
    0.61
     Natasha
    0.61
    guards
    0.60
     Coach
    0.60
     where
    0.59
    Activations Density 0.256%

    No Known Activations