© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 1-RES-JB
    6. 943
    Prev
    Next
    INDEX
    Explanations

    phrases related to NASA's Goddard Institute for Space Studies

    oai_token-act-pair · gpt-3.5-turbo

    references to the Goddard Space Institute and associated keywords

    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
    ategory
    -0.94
    ozo
    -0.90
    assic
    -0.90
    osuke
    -0.90
    oho
    -0.88
    ecause
    -0.88
    anism
    -0.85
    antha
    -0.84
    usal
    -0.83
    istan
    -0.82
    POSITIVE LOGITS
     Goddard
    0.77
     actionGroup
    0.76
     Grimes
    0.75
     ambient
    0.74
    maid
    0.73
     Pressure
    0.73
     instruments
    0.69
     Europa
    0.68
     Terminal
    0.66
    EMP
    0.65
    Activations Density 0.026%

    No Known Activations