© 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. 7-RES-JB
    11. 3643
    Prev
    Next
    INDEX
    Explanations

    commands or instructions related to programming and file manipulation

    oai_token-act-pair · gpt-3.5-turbo

    programming or technical keywords related to file management and system commands

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iquid
    -0.63
    AIR
    -0.62
    interstitial
    -0.60
    arios
    -0.60
    bite
    -0.60
     captivity
    -0.60
    markets
    -0.59
    waters
    -0.59
    JR
    -0.59
    Ark
    -0.58
    POSITIVE LOGITS
     shorthand
    0.81
    solete
    0.75
    SourceFile
    0.72
     instant
    0.69
    pload
    0.69
     overwrite
    0.69
    inarily
    0.68
     alias
    0.68
     abbre
    0.67
     Variant
    0.67
    Activations Density 0.311%

    No Known Activations