© 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. 4-RES-JB
    6. 6565
    Prev
    Next
    INDEX
    Explanations

    references to a single-payer healthcare system

    oai_token-act-pair · gpt-3.5-turbo

    terms related to single-payer healthcare systems

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

    No Comments

    Negative Logits
    ampton
    -0.73
     Cannes
    -0.70
     Schwar
    -0.68
     Sorcerer
    -0.67
    orian
    -0.66
    eele
    -0.65
     Mehran
    -0.63
    occ
    -0.62
    umn
    -0.62
     Scor
    -0.61
    POSITIVE LOGITS
    payer
    1.03
    ysis
    0.84
     beware
    0.81
    rehensive
    0.80
    yright
    0.79
    backer
    0.78
    vernment
    0.74
    riors
    0.73
    ublic
    0.72
    heed
    0.69
    Activations Density 0.011%

    No Known Activations