© 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. 1-RES-JB
    11. 9409
    Prev
    Next
    INDEX
    Explanations

    technical terms related to voltage and electrical engineering

    oai_token-act-pair · gpt-3.5-turbo

    terms related to voltage and electric currents

    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
    xia
    -0.84
     McKay
    -0.82
    apolis
    -0.79
     Bei
    -0.78
    elly
    -0.71
     Landing
    -0.70
    verett
    -0.70
    pard
    -0.70
    andon
    -0.68
     Raider
    -0.67
    POSITIVE LOGITS
     volt
    1.29
    volt
    1.26
     voltage
    1.21
     volts
    1.15
     Voltage
    1.03
    ulner
    0.94
     amps
    0.88
     Volt
    0.83
    atility
    0.80
     circuitry
    0.76
    Activations Density 0.013%

    No Known Activations