© 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. 4476
    Prev
    Next
    INDEX
    Explanations

    specific numerical values related to power capacity in megawatts

    oai_token-act-pair · gpt-3.5-turbo

    references to megawatt (MW) power capacity

    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
    bart
    -0.64
     psy
    -0.64
     Labrador
    -0.64
     communist
    -0.63
    kick
    -0.63
     MacArthur
    -0.63
    voy
    -0.61
    amount
    -0.60
     Fract
    -0.60
    leans
    -0.59
    POSITIVE LOGITS
    MW
    1.31
    atts
    1.00
    NT
    0.98
    ILA
    0.92
    ESH
    0.91
     MW
    0.89
    LAN
    0.89
    ILD
    0.89
    ILY
    0.89
    Fs
    0.87
    Activations Density 0.005%

    No Known Activations