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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    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. 2-RES-JB
    6. 17954
    Prev
    Next
    INDEX
    Explanations

    words related to a specific time frame or duration

    oai_token-act-pair · gpt-3.5-turbo

    phrases that indicate a specific timeframe or context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Genie
    -0.70
     mer
    -0.66
     rot
    -0.65
     devil
    -0.65
     por
    -0.64
    alian
    -0.64
     rag
    -0.62
     buff
    -0.61
    di
    -0.61
     flare
    -0.60
    POSITIVE LOGITS
    ieth
    0.89
    isine
    0.86
    ¥ŀ
    0.85
     oun
    0.84
     Seconds
    0.84
     Survive
    0.84
    ĵĺ
    0.81
    ths
    0.79
    ournal
    0.79
    Days
    0.78
    Activations Density 0.008%

    No Known Activations