© 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 EvalsExportsinterp-engineNEWAPI 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. 9555
    Prev
    Next
    INDEX
    Explanations

    the mention of computer hardware specifications related to memory (RAM)

    oai_token-act-pair · gpt-3.5-turbo

    references to RAM in technical contexts

    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
    kef
    -0.80
    rique
    -0.77
    reek
    -0.74
     Daniels
    -0.73
     Foley
    -0.72
    ertain
    -0.68
    weather
    -0.65
    hold
    -0.65
    terson
    -0.64
    ocrin
    -0.64
    POSITIVE LOGITS
    mers
    0.86
    disk
    0.85
    MY
    0.82
    ming
    0.77
    RAM
    0.77
     RAM
    0.77
    MER
    0.77
    MIT
    0.76
    LOAD
    0.75
    Disk
    0.74
    Activations Density 0.009%

    No Known Activations