© 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. 0-RES-JB
    11. 22226
    Prev
    Next
    INDEX
    Explanations

    mentions of the term "Atlas"

    oai_token-act-pair · gpt-3.5-turbo

    references to the Atlas 9 rocket

    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
    ¨
    -0.81
    ially
    -0.71
    cream
    -0.69
    ews
    -0.67
    ptr
    -0.67
    lee
    -0.65
    \<
    -0.64
     kn
    -0.64
     dairy
    -0.64
    ãģ¦
    -0.64
    POSITIVE LOGITS
     Atlas
    4.29
    las
    1.23
     Minotaur
    1.23
     Beacon
    1.19
     Titan
    1.14
     Vale
    1.09
     Ares
    1.07
     Inventory
    1.07
     Canaveral
    1.06
     Asgard
    1.03
    Activations Density 0.022%

    No Known Activations