© 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. 18067
    Prev
    Next
    INDEX
    Explanations

    mentions of a specific name "Helmholtz"

    oai_token-act-pair · gpt-3.5-turbo

    references to specific notable individuals or names

    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
     welfare
    -0.64
     liber
    -0.60
     prison
    -0.59
     commercial
    -0.58
     charity
    -0.58
     primarily
    -0.58
     drug
    -0.58
     criminals
    -0.57
     Birmingham
    -0.57
     drains
    -0.55
    POSITIVE LOGITS
    tz
    5.01
    etz
    1.24
    tsky
    1.23
    tch
    1.08
    chuk
    1.08
    itsch
    1.07
    atz
    1.07
    yy
    1.07
    hz
    1.05
    icz
    1.04
    Activations Density 0.013%

    No Known Activations