© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 2-RES-JB
    11. 12428
    Prev
    Next
    INDEX
    Explanations

    content related to additional items or features provided beyond the basic offering

    oai_token-act-pair · gpt-3.5-turbo

    references to additional features or content in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Cola
    -0.76
    Pa
    -0.74
    Mos
    -0.74
    uez
    -0.70
    States
    -0.69
    ggles
    -0.69
     Records
    -0.69
     Investigative
    -0.66
    ez
    -0.66
    Govern
    -0.66
    POSITIVE LOGITS
     extras
    1.50
     goodies
    1.07
     challeng
    0.81
    visor
    0.80
     virgin
    0.74
    alon
    0.74
     costumes
    0.71
    ubs
    0.71
    ãģĨ
    0.70
    ervatives
    0.70
    Activations Density 0.005%

    No Known Activations