© 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. 12-RES-JB
    11. 2993
    Prev
    Next
    INDEX
    Explanations

    features and specifications of PlayStation consoles

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    terms related to gaming hardware and features

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 12-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.hook_resid_post
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    atories
    -0.81
    tnc
    -0.72
    heng
    -0.71
    atory
    -0.71
     Manz
    -0.71
    trump
    -0.70
    elong
    -0.70
     Christensen
    -0.69
    ndra
    -0.69
    oros
    -0.68
    POSITIVE LOGITS
     controller
    1.05
     Slim
    1.04
     Controller
    1.02
     controllers
    1.00
     emulator
    0.97
     consoles
    0.95
     owners
    0.93
     version
    0.93
     exclusive
    0.91
     versions
    0.90
    Activations Density 0.073%

    No Known Activations