© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 6-RES-JB
    11. 16835
    Prev
    Next
    INDEX
    Explanations

    mentions of the word 'multi'

    oai_token-act-pair · gpt-3.5-turbo

    instances of the prefix "multi-" indicating a multiplicity or multiple aspects of a subject

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    UTION
    -0.76
     Bauer
    -0.75
     Curve
    -0.72
     Butcher
    -0.71
    IONS
    -0.69
     Gleaming
    -0.69
    士
    -0.69
     Wonderland
    -0.67
    çĶ°
    -0.66
     Gors
    -0.66
    POSITIVE LOGITS
    ples
    1.17
    icult
    0.93
    cro
    0.90
    platform
    0.88
    player
    0.87
    employ
    0.87
    absor
    0.85
    acet
    0.85
    unit
    0.85
    urally
    0.84
    Activations Density 0.017%

    No Known Activations