© 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. 4-RES-JB
    11. 23695
    Prev
    Next
    INDEX
    Explanations

    terms related to voltage and electrical systems

    oai_token-act-pair · gpt-3.5-turbo

    terms related to voltage and electrical energy

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

    No Comments

    Negative Logits
     Bei
    -0.84
     McKay
    -0.81
    pard
    -0.76
    apolis
    -0.74
    neys
    -0.74
    gotten
    -0.72
    fman
    -0.72
    ovember
    -0.71
    chery
    -0.71
    iak
    -0.70
    POSITIVE LOGITS
     voltage
    1.05
     volt
    1.02
     volts
    1.02
    volt
    0.94
    atility
    0.92
     Voltage
    0.90
     amps
    0.84
     fluctuations
    0.82
     converter
    0.76
     amplifier
    0.76
    Activations Density 0.015%

    No Known Activations