© 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. 10383
    Prev
    Next
    INDEX
    Explanations

    references to a specific name, "Dutch", likely related to different entities or persons with this name

    oai_token-act-pair · gpt-3.5-turbo

    terms related to clutches and superstition

    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
     Gly
    -0.74
     Ples
    -0.73
     salts
    -0.71
     Ras
    -0.68
     Authorization
    -0.66
     Networks
    -0.65
     RAND
    -0.64
     Alphabet
    -0.64
     Boo
    -0.63
     augmented
    -0.63
    POSITIVE LOGITS
    utch
    3.88
     superst
    1.91
     clutch
    1.80
    essel
    0.96
    ackle
    0.91
     Hutch
    0.89
    uture
    0.85
    etter
    0.83
     clut
    0.82
    utter
    0.81
    Activations Density 0.028%

    No Known Activations