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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 7994
    Prev
    Next
    INDEX
    Explanations

    information related to physical attributes or characteristics of biological subjects, such as growth rates, brain activity, skin properties, and cell division

    oai_token-act-pair · gpt-3.5-turbo

    terms related to biological structures and functions

    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
    wered
    -0.80
    ilitary
    -0.80
    mercial
    -0.77
    licted
    -0.73
    deal
    -0.69
    quished
    -0.67
    aniel
    -0.67
    nces
    -0.67
    ulhu
    -0.66
     Nare
    -0.66
    POSITIVE LOGITS
     morphology
    1.27
     responsiveness
    1.15
     composition
    1.13
     density
    1.12
     physiology
    1.11
     metabolism
    1.10
     characteristics
    1.09
     activity
    1.07
     thickness
    1.06
     dynamics
    1.05
    Activations Density 0.186%

    No Known Activations