© 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. 4-RES-JB
    11. 13156
    Prev
    Next
    INDEX
    Explanations

    mentions of lawmakers

    oai_token-act-pair · gpt-3.5-turbo

    references to lawmakers and legislative activities

    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
    ãĤ¨ãĥ«
    -0.90
    --+
    -0.71
    thritis
    -0.68
    phal
    -0.67
     Carbuncle
    -0.66
    forest
    -0.65
     Vertical
    -0.64
     Knock
    -0.63
    omorph
    -0.60
    uras
    -0.60
    POSITIVE LOGITS
    arians
    0.96
    woman
    0.95
    hip
    0.91
    hips
    0.90
    ervatives
    0.88
     redist
    0.78
    interstitial
    0.77
     lawmakers
    0.74
    ileaks
    0.72
    bourg
    0.71
    Activations Density 0.025%

    No Known Activations