© 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. 16790
    Prev
    Next
    INDEX
    Explanations

    temporal references or time-related phrases

    oai_token-act-pair · gpt-3.5-turbo

    temporal references and expressions of time

    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
     vulner
    -0.73
     Seym
    -0.72
     destro
    -0.72
     challeng
    -0.69
     Vaugh
    -0.68
     helicop
    -0.64
     withd
    -0.62
     advoc
    -0.61
     cryst
    -0.59
     Azerb
    -0.59
    POSITIVE LOGITS
    ':
    0.66
    erity
    0.64
    \":
    0.63
    ndra
    0.63
    ihad
    0.61
    hat
    0.59
    cigarettes
    0.57
    Ĥİ
    0.57
    Ĥª
    0.56
    ctive
    0.55
    Activations Density 0.864%

    No Known Activations