© 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 EvalsExportsinterp-engineNEWAPI 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. 9-RES-JB
    11. 23460
    Prev
    Next
    INDEX
    Explanations

    information related to health benefits and risks associated with food and lifestyle choices

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to health and dietary impacts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    arna
    -0.74
    phabet
    -0.71
     acknowledgement
    -0.67
    iku
    -0.66
    rentices
    -0.66
     Peb
    -0.66
    EStreamFrame
    -0.65
    ighting
    -0.65
     wishes
    -0.64
     Obj
    -0.64
    POSITIVE LOGITS
     beneficial
    1.24
     detrimental
    1.16
     impair
    1.16
     negatively
    1.09
     adversely
    1.04
     stimulating
    1.03
     inhibit
    1.02
     positively
    1.01
     calming
    1.01
     correlated
    1.00
    Activations Density 0.525%

    No Known Activations