© 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. 10-RES-JB
    11. 3130
    Prev
    Next
    INDEX
    Explanations

    phrases related to molecular biology and gene expression

    oai_token-act-pair · gpt-3.5-turbo

    biochemical signaling processes related to neuronal expression

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĤ£
    -0.90
    Kick
    -0.89
    Phone
    -0.85
    Enlarge
    -0.80
    Throw
    -0.80
    think
    -0.79
    Mist
    -0.79
    Tech
    -0.78
    Advertisement
    -0.77
    Business
    -0.77
    POSITIVE LOGITS
     endogenous
    1.19
     cortical
    1.06
     mammalian
    1.06
     âĪ¼
    1.05
     extant
    1.02
     α
    0.99
     neuronal
    0.99
     phen
    0.97
     β
    0.97
     differential
    0.97
    Activations Density 0.343%

    No Known Activations