Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 8-RES-JB
    6. 4146
    Prev
    Next
    INDEX
    Explanations

    words related to official positions in government or political press briefings

    oai_token-act-pair · gpt-3.5-turbo

    terms related to press secretaries and their roles within the White House

    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
     mould
    -0.71
     slaughter
    -0.66
    uries
    -0.66
     drought
    -0.64
    uckland
    -0.63
     steril
    -0.62
     landlords
    -0.62
     relegation
    -0.62
     tuberculosis
    -0.61
     [|
    -0.61
    POSITIVE LOGITS
     Sean
    0.96
     Katie
    0.86
     Ari
    0.84
     Trey
    0.80
     Huma
    0.80
     Dmitry
    0.75
    afort
    0.75
     Nicole
    0.74
     Priebus
    0.72
     Suzanne
    0.72
    Activations Density 0.116%

    No Known Activations