© 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. 8-RES-JB
    11. 22595
    Prev
    Next
    INDEX
    Explanations

    the word "this" preceding a situation or point in time specified in the text

    oai_token-act-pair · gpt-3.5-turbo

    references to the present moment or current context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    letters
    -0.71
    renheit
    -0.68
    ilus
    -0.67
    stained
    -0.60
    onis
    -0.59
    packages
    -0.59
    adden
    -0.58
    inis
    -0.58
    forcement
    -0.57
    omo
    -0.57
    POSITIVE LOGITS
     jun
    1.15
     point
    1.05
    point
    0.95
     moment
    0.94
     level
    0.91
     behest
    0.89
     junction
    0.85
     rate
    0.83
     outset
    0.82
     stage
    0.82
    Activations Density 0.037%

    No Known Activations