© 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. 10-RES-JB
    6. 11083
    Prev
    Next
    INDEX
    Explanations

    phrases related to news reports and information dissemination

    oai_token-act-pair · gpt-3.5-turbo

    news outlet references and report updates

    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
    Ohio
    -1.09
     Buc
    -1.07
     Akron
    -1.00
     Cleveland
    -1.00
    chwitz
    -0.99
     Cavs
    -0.97
    lehem
    -0.96
     Polish
    -0.96
     Ohio
    -0.93
     Sloven
    -0.93
    POSITIVE LOGITS
     Canberra
    2.04
     Australians
    1.93
     NSW
    1.92
     Tasmania
    1.91
    Austral
    1.91
     Australian
    1.90
     Australia
    1.88
     Brisbane
    1.87
     Queensland
    1.87
    Australian
    1.86
    Activations Density 0.862%

    No Known Activations