© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 9-RES-JB
    11. 18556
    Prev
    Next
    INDEX
    Explanations

    questions or assertions about identifying a specific person or entity

    oai_token-act-pair · gpt-3.5-turbo

    references to unidentified individuals or inquiries about identity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    framework
    -0.73
    MER
    -0.69
     Globe
    -0.65
    ranging
    -0.65
    eme
    -0.65
     guiActiveUnfocused
    -0.64
    requ
    -0.64
    retion
    -0.63
    emin
    -0.62
    IVE
    -0.61
    POSITIVE LOGITS
     else
    1.15
    soever
    1.11
     owns
    0.97
     cares
    0.92
     knows
    0.91
     pays
    0.90
    abouts
    0.88
     owes
    0.87
    ever
    0.85
    oping
    0.84
    Activations Density 0.057%

    No Known Activations