© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 0-RES-JB
    6. 6370
    Prev
    Next
    INDEX
    Explanations

    phrases related to email addresses

    oai_token-act-pair · gpt-3.5-turbo

    instances of the term "pa" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Dirt
    -0.71
     Transformers
    -0.64
     Hunts
    -0.61
     mete
    -0.60
     Rouse
    -0.60
     bleach
    -0.60
     def
    -0.58
     depiction
    -0.57
     commod
    -0.57
     Defenders
    -0.57
    POSITIVE LOGITS
    pa
    4.57
    pas
    2.81
    Pa
    1.51
    PA
    1.48
     pa
    1.35
    pi
    1.34
    pan
    1.33
    apa
    1.30
     Pa
    1.19
    po
    1.19
    Activations Density 0.010%

    No Known Activations