© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 18669
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a shift or transition in a situation or context

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "Now" and its variations in 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
     [|
    -0.82
    acci
    -0.67
    VERTISEMENT
    -0.66
    icidal
    -0.63
    "},{"
    -0.60
    Interstitial
    -0.60
    chest
    -0.60
    aughed
    -0.59
    println
    -0.59
    cos
    -0.58
    POSITIVE LOGITS
    adays
    1.58
    here
    1.10
    heres
    0.78
     defunct
    0.78
    nir
    0.77
     NCT
    0.75
    IRT
    0.71
     embattled
    0.71
    terday
    0.70
     Deadline
    0.70
    Activations Density 0.061%

    No Known Activations