© 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. 8-RES-JB
    6. 17160
    Prev
    Next
    INDEX
    Explanations

    time-related events or facts

    oai_token-act-pair · gpt-3.5-turbo

    mentions of age and time in relation to events

    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
    erenn
    -0.74
     detach
    -0.74
    annel
    -0.69
    cffff
    -0.67
    una
    -0.67
    esa
    -0.65
     dispel
    -0.65
    unity
    -0.62
    =-=-
    -0.62
    eno
    -0.62
    POSITIVE LOGITS
     original
    0.79
     pictured
    0.74
     impetus
    0.71
     originally
    0.69
     fateful
    0.68
    orig
    0.68
    arnaev
    0.67
     Simpson
    0.66
     Yanuk
    0.65
     referenced
    0.65
    Activations Density 0.916%

    No Known Activations