© 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 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. 14593
    Prev
    Next
    INDEX
    Explanations

    names related to people or characters

    oai_token-act-pair · gpt-3.5-turbo

    the term "os," suggesting a focus on technical domain-specific language or identifiers

    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
     CTR
    -0.68
    ãĥ¬
    -0.67
    è¦ļéĨĴ
    -0.66
     Cox
    -0.65
     fixme
    -0.65
    ãĥ©ãĥ³
    -0.64
    æĸ
    -0.62
     Interior
    -0.62
     grounds
    -0.61
     plain
    -0.61
    POSITIVE LOGITS
    hiba
    1.36
    omething
    1.12
    ophy
    1.11
    ophical
    1.11
    leep
    1.08
    hea
    1.04
    opher
    1.03
    ocial
    0.99
    mith
    0.99
    iris
    0.98
    Activations Density 0.024%

    No Known Activations