© 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. 0-RES-JB
    6. 11444
    Prev
    Next
    INDEX
    Explanations

    magnitude of numeric values

    oai_token-act-pair · gpt-3.5-turbo

    phrases related to the concept of magnitude, particularly in contexts like earthquakes or significant events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aways
    -0.68
     Match
    -0.67
    open
    -0.64
    walk
    -0.62
     Talks
    -0.62
    sta
    -0.61
    cour
    -0.60
     Driver
    -0.60
    Chat
    -0.60
    lyn
    -0.60
    POSITIVE LOGITS
     magnitude
    4.10
     scale
    1.45
     severity
    1.44
     enorm
    1.37
     amplitude
    1.33
     intensity
    1.26
     degree
    1.23
     magn
    1.22
     caliber
    1.21
     significance
    1.20
    Activations Density 0.009%

    No Known Activations