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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 4-RES-JB
    6. 21878
    Prev
    Next
    INDEX
    Explanations

    mentions of specific locations and dates

    oai_token-act-pair · gpt-3.5-turbo

    sentences that end with a period

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

    No Comments

    Negative Logits
     metic
    -0.84
     brut
    -0.83
     tack
    -0.83
     prey
    -0.80
     extinct
    -0.79
     everywhere
    -0.79
     everyday
    -0.77
     adversary
    -0.77
     quir
    -0.76
     fishes
    -0.76
    POSITIVE LOGITS
     Additionally
    1.09
     Afterwards
    1.07
     However
    1.04
     Along
    1.04
     Later
    1.03
     Previously
    1.02
     Interestingly
    1.00
     According
    0.99
     Meanwhile
    0.98
     During
    0.98
    Activations Density 0.911%

    No Known Activations