© 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. 3-RES-JB
    11. 6466
    Prev
    Next
    INDEX
    Explanations

    words related to magnitudes or levels of intensity

    oai_token-act-pair · gpt-3.5-turbo

    variations of the word "magnify" and its related forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    BOOK
    -0.91
    OPLE
    -0.91
    pta
    -0.77
    thia
    -0.74
     Alive
    -0.73
     Defenders
    -0.70
    FO
    -0.69
     Bleach
    -0.67
    EEE
    -0.67
    RT
    -0.67
    POSITIVE LOGITS
    itudes
    1.09
    ificent
    1.06
    ific
    1.03
    olia
    1.00
     magn
    0.97
    animous
    0.96
     glim
    0.87
     tremend
    0.87
    ifying
    0.86
    itud
    0.85
    Activations Density 0.005%

    No Known Activations