© 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. 0-RES-JB
    11. 8415
    Prev
    Next
    INDEX
    Explanations

    adjectives ending in 'hered'

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "tethered."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Gas
    -0.67
     background
    -0.67
     ber
    -0.65
     gas
    -0.65
     import
    -0.61
     street
    -0.60
     ACE
    -0.60
     loading
    -0.60
     Dean
    -0.59
     stopp
    -0.59
    POSITIVE LOGITS
    hered
    5.34
    heres
    1.72
    hers
    1.28
    herer
    1.27
    ched
    1.22
    pered
    1.16
    ivated
    1.12
    kered
    1.09
    hed
    1.08
    hesion
    1.05
    Activations Density 0.016%

    No Known Activations