Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 23817
    Prev
    Next
    INDEX
    Explanations

    phrases starting with "These" that denote a group or collection of related items or concepts

    oai_token-act-pair · gpt-3.5-turbo

    phrases that start with "These," indicating a focus on specific examples or instances

    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
     surgery
    -0.65
     paperwork
    -0.64
     anyway
    -0.63
     vice
    -0.58
     coach
    -0.57
     wound
    -0.56
     officially
    -0.56
     backup
    -0.56
     staff
    -0.56
     barely
    -0.56
    POSITIVE LOGITS
     These
    2.94
    These
    2.48
     THESE
    2.04
    these
    1.99
     Those
    1.85
     Such
    1.66
     This
    1.59
     Each
    1.51
    Those
    1.46
     They
    1.46
    Activations Density 0.015%

    No Known Activations