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. 410
    Prev
    Next
    INDEX
    Explanations

    words related to magnification or emphasis

    oai_token-act-pair · gpt-3.5-turbo

    terms related to the concept of 'magnitude' or 'greatness.'

    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
    BOOK
    -0.98
    OPLE
    -0.96
    pta
    -0.71
    âĸ¬âĸ¬
    -0.71
    thia
    -0.70
     Rite
    -0.69
    FAULT
    -0.69
     Warriors
    -0.69
     Alive
    -0.68
    FO
    -0.68
    POSITIVE LOGITS
    itudes
    1.16
    ific
    1.14
    ificent
    1.10
    olia
    1.07
    animous
    1.02
    ifying
    0.93
    itude
    0.93
     magn
    0.93
    ified
    0.91
    itud
    0.91
    Activations Density 0.007%

    No Known Activations