© 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. 3762
    Prev
    Next
    INDEX
    Explanations

    terms related to academia and technology in various contexts

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

    elements related to the convergence of technology and business sectors

    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
     downgrade
    -0.89
     inacc
    -0.87
     punishments
    -0.87
     redacted
    -0.86
     torture
    -0.84
     suspensions
    -0.83
     punishment
    -0.82
     censored
    -0.81
     gag
    -0.81
     inconsist
    -0.81
    POSITIVE LOGITS
    à¼
    1.09
    ãĢ
    1.06
     pione
    1.04
    Laun
    1.04
    apult
    1.02
    Built
    0.98
    Þ
    0.96
    reprene
    0.96
    ô
    0.96
     entreprene
    0.94
    Activations Density 1.075%

    No Known Activations