© 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. 4-RES-JB
    11. 20830
    Prev
    Next
    INDEX
    Explanations

    adjectives and verbs related to physical and emotional states

    oai_token-act-pair · gpt-3.5-turbo

    terms related to health, well-being, and viral phenomena

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

    No Comments

    Negative Logits
    cest
    -0.75
     href
    -0.71
     Scal
    -0.65
    gotten
    -0.63
    jection
    -0.62
     ML
    -0.61
     Inner
    -0.59
     Pod
    -0.58
    Wo
    -0.56
    operation
    -0.56
    POSITIVE LOGITS
     srfAttach
    0.90
    retty
    0.81
    aneously
    0.81
    ntil
    0.77
     whilst
    0.75
    izont
    0.73
    DAQ
    0.70
     asleep
    0.66
     indoors
    0.66
     amidst
    0.66
    Activations Density 0.332%

    No Known Activations