© 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. 14860
    Prev
    Next
    INDEX
    Explanations

    information related to magnetic fields

    oai_token-act-pair · gpt-3.5-turbo

    terms associated with magnetic fields and their scientific implications

    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
    ership
    -0.90
    20439
    -0.86
     Columb
    -0.76
    EY
    -0.76
    IVERS
    -0.75
    EU
    -0.75
    ELL
    -0.73
    IRD
    -0.71
    chens
    -0.71
     Kut
    -0.70
    POSITIVE LOGITS
     resonance
    1.11
     compass
    1.11
     magnetic
    1.07
    netic
    1.04
     stripes
    0.98
     poles
    0.97
     susceptibility
    0.96
     anomaly
    0.92
     pulse
    0.91
     currents
    0.90
    Activations Density 0.009%

    No Known Activations