© 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. 11-RES-JB
    6. 16602
    Prev
    Next
    INDEX
    Explanations

    keywords related to personal data or details about individuals such as names, health information, and personal events

    oai_token-act-pair · gpt-3.5-turbo

    nouns and terms related to personal identification and bureaucratic processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     oneself
    -0.78
     themselves
    -0.77
     Helpful
    -0.75
     ourselves
    -0.72
     yourselves
    -0.66
     guiName
    -0.65
    those
    -0.64
    necessary
    -0.63
    rather
    -0.62
    aples
    -0.62
    POSITIVE LOGITS
     consisted
    1.04
     wasn
    1.01
     hasn
    1.00
     was
    1.00
     consists
    0.99
     resembles
    0.96
     coincided
    0.95
     contains
    0.92
     lasted
    0.91
    mate
    0.91
    Activations Density 0.357%

    No Known Activations