© 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. 8-RES-JB
    11. 20384
    Prev
    Next
    INDEX
    Explanations

    terms related to technical instructions or settings adjustments

    oai_token-act-pair · gpt-3.5-turbo

    instructions related to software settings and configurations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iard
    -0.70
    dfx
    -0.70
     anarchist
    -0.69
    pherd
    -0.68
     laz
    -0.68
    assic
    -0.68
    lycer
    -0.68
    dain
    -0.67
     satir
    -0.66
    umpy
    -0.66
    POSITIVE LOGITS
     Settings
    1.34
     Preferences
    1.21
     Properties
    1.20
    Settings
    1.08
     Options
    1.05
     Configuration
    1.03
    Tools
    0.99
     Ribbon
    0.98
     Devices
    0.96
    Appearance
    0.96
    Activations Density 0.149%

    No Known Activations