© 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. 10-RES-JB
    11. 12803
    Prev
    Next
    INDEX
    Explanations

    quantities associated with kilowatts

    oai_token-act-pair · gpt-3.5-turbo

    units of measurement related to kilowatt hours and its various uses

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Fargo
    -0.74
     Solitaire
    -0.72
     CoC
    -0.70
    ACE
    -0.68
    éĹĺ
    -0.61
    ARP
    -0.60
     Flight
    -0.60
     malf
    -0.60
     ACS
    -0.59
     Barcl
    -0.59
    POSITIVE LOGITS
    ogram
    1.46
    oby
    1.43
    ometer
    1.28
    oton
    1.21
    ograms
    1.19
    ometers
    1.18
    omet
    1.03
    ographed
    1.02
    tern
    1.00
    ograph
    0.96
    Activations Density 0.020%

    No Known Activations