© 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. 10-RES-JB
    11. 13608
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to various subjects or fields such as people, places, or concepts

    oai_token-act-pair · gpt-3.5-turbo

    names and terms related to notable individuals, events, and phenomena

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Synopsis
    -0.73
    è¦
    -0.66
    »Ĵ
    -0.65
    soever
    -0.64
     Airl
    -0.63
    idav
    -0.62
     ILCS
    -0.62
    onnaissance
    -0.61
    itant
    -0.60
     )]
    -0.60
    POSITIVE LOGITS
     existed
    1.09
     wasn
    1.08
     could
    1.07
     was
    1.05
     exists
    1.04
     hadn
    0.98
     belonged
    0.96
     isn
    0.95
     wouldn
    0.94
     hasn
    0.94
    Activations Density 0.390%

    No Known Activations