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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 6-RES-JB
    6. 3094
    Prev
    Next
    INDEX
    Explanations

    keywords related to technology and settings configuration

    oai_token-act-pair · gpt-3.5-turbo

    terms related to specialized services, features, or accounts

    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
    terday
    -0.85
    itably
    -0.83
    iannopoulos
    -0.79
    anwhile
    -0.75
    etheless
    -0.71
    olson
    -0.68
    yright
    -0.66
     republican
    -0.65
     laz
    -0.64
    ounter
    -0.64
    POSITIVE LOGITS
     Mode
    1.09
     Definition
    1.04
     Manager
    1.04
     Points
    1.01
     Selection
    1.00
     Methods
    0.98
     Settings
    0.97
     Mechanics
    0.96
     Characters
    0.95
     Builder
    0.94
    Activations Density 0.479%

    No Known Activations