© 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. 20614
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to historical or political entities

    oai_token-act-pair · gpt-3.5-turbo

    references to the term "Imperial"

    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
    Downloadha
    -0.90
    WAYS
    -0.76
    NetMessage
    -0.75
    printf
    -0.75
    liest
    -0.74
    earance
    -0.74
    cence
    -0.74
    BOOK
    -0.73
    trak
    -0.70
    rooms
    -0.68
    POSITIVE LOGITS
    perial
    1.43
     Imperial
    0.93
     imperial
    0.90
     Empire
    0.84
     glim
    0.79
     oun
    0.77
    perors
    0.73
     patronage
    0.73
    rament
    0.72
     legion
    0.71
    Activations Density 0.009%

    No Known Activations