© 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. 2-RES-JB
    6. 12066
    Prev
    Next
    INDEX
    Explanations

    special characters "{" and "}"

    oai_token-act-pair · gpt-3.5-turbo

    sections of text that indicate importance or relevance, potentially in a form of evaluation or discussion

    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
    hement
    -0.77
    etheless
    -0.72
     endeavour
    -0.70
     honoured
    -0.70
    uca
    -0.69
     estranged
    -0.69
     diving
    -0.66
     imperson
    -0.66
     hust
    -0.65
     unsuspecting
    -0.65
    POSITIVE LOGITS
    ³³³³³³³³³³³³³³³³
    1.04
    ³³³³
    1.03
    ³³³³³³³³
    0.99
    Posted
    0.97
    ................................................................
    0.90
    ³³³
    0.89
    Loading
    0.88
    Advertisement
    0.86
    Newsletter
    0.85
    Recommended
    0.85
    Activations Density 1.474%

    No Known Activations