© 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. 1-RES-JB
    11. 4849
    Prev
    Next
    INDEX
    Explanations

    the word "Sho"

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific individual or entity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MC
    -0.68
    BuyableInstoreAndOnline
    -0.67
    illary
    -0.66
    anwhile
    -0.66
    sen
    -0.65
     ACLU
    -0.64
     Lethal
    -0.64
     Suffolk
    -0.63
    enegger
    -0.63
    orset
    -0.62
    POSITIVE LOGITS
     Sho
    1.26
    zzle
    0.94
    velt
    0.93
    emaker
    0.87
    hei
    0.87
    aku
    0.85
    ogi
    0.82
    adier
    0.81
    izont
    0.76
    lette
    0.76
    Activations Density 0.004%

    No Known Activations