© 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. 2-RES-JB
    11. 4453
    Prev
    Next
    INDEX
    Explanations

    phrases related to galaxies

    oai_token-act-pair · gpt-3.5-turbo

    references to "galactic" themes and concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    BOOK
    -0.73
    orters
    -0.63
    uncture
    -0.63
     fateful
    -0.63
     established
    -0.62
     compr
    -0.62
    erous
    -0.62
     RIP
    -0.61
     archived
    -0.60
    akening
    -0.60
    POSITIVE LOGITS
    axy
    1.15
    gal
    1.10
    axies
    1.06
     ILCS
    0.93
    pha
    0.84
    actic
    0.83
    odon
    0.83
    actus
    0.83
    iev
    0.81
    itary
    0.79
    Activations Density 0.010%

    No Known Activations