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

    Neuronpedia

    Jacobian LensNEW
    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. 6-RES-JB
    11. 2596
    Prev
    Next
    INDEX
    Explanations

    words related to biochemistry, specifically focusing on substances like "pathogen", "cryogen", and "homogen"

    oai_token-act-pair · gpt-3.5-turbo

    terms related to biological processes and compounds

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    angled
    -0.74
    eneg
    -0.70
    hovah
    -0.70
    icult
    -0.68
    real
    -0.68
    riage
    -0.68
     Pradesh
    -0.67
    avorite
    -0.66
    alion
    -0.65
    iculty
    -0.65
    POSITIVE LOGITS
    etic
    1.34
    etics
    1.31
    etically
    1.24
    ously
    1.11
    ocide
    1.09
    esis
    1.08
    士
    0.99
    alogy
    0.95
    icity
    0.91
    izational
    0.88
    Activations Density 0.032%

    No Known Activations