© 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. 1817
    Prev
    Next
    INDEX
    Explanations

    information related to politics and current events, such as political candidates and government agencies

    oai_token-act-pair · gpt-3.5-turbo

    aspects related to sports teams and political candidates

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    ĸļ
    -0.69
    Staff
    -0.60
    Correct
    -0.58
    truth
    -0.58
    Words
    -0.58
    lled
    -0.58
    leanor
    -0.57
    VERTISEMENT
    -0.56
    istered
    -0.56
    ributed
    -0.56
    POSITIVE LOGITS
     currently
    0.89
     notoriously
    0.88
     rumored
    0.80
     traditionally
    0.80
     famously
    0.79
     billionaire
    0.78
     already
    0.77
     looming
    0.77
     ostensibly
    0.77
     theoretically
    0.77
    Activations Density 1.130%

    No Known Activations