© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 0-RES-JB
    11. 14735
    Prev
    Next
    INDEX
    Explanations

    medical conditions and legal terms related to burdensome or heavy restrictions or obligations

    oai_token-act-pair · gpt-3.5-turbo

    terms associated with danger and serious health conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    chest
    -0.74
     Prediction
    -0.66
    visor
    -0.65
     Continuous
    -0.64
    ãĥ¼ãĥ
    -0.64
     Hidden
    -0.63
    cover
    -0.61
    range
    -0.60
     Ans
    -0.60
    pose
    -0.60
    POSITIVE LOGITS
    erous
    2.83
    anity
    2.09
     sclerosis
    1.81
    pox
    1.30
    clus
    1.29
    weed
    1.20
    clerosis
    1.16
    pter
    1.13
    unky
    1.10
    maid
    1.09
    Activations Density 0.058%

    No Known Activations