© 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. 7917
    Prev
    Next
    INDEX
    Explanations

    phrases related to comparison and positioning, particularly using words such as "above" or "over"

    oai_token-act-pair · gpt-3.5-turbo

    the term "Above" and related phrases in the context of numerical measures or rankings

    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
     birthday
    -0.62
    ctors
    -0.62
     thanks
    -0.54
    ization
    -0.54
    fest
    -0.53
    hol
    -0.52
     thank
    -0.52
    rolled
    -0.52
     non
    -0.51
     comeback
    -0.51
    POSITIVE LOGITS
     Above
    3.75
    above
    3.14
    Above
    3.07
     above
    2.28
    below
    2.02
     BELOW
    1.61
     Below
    1.61
    Below
    1.39
     below
    1.35
     Beyond
    1.06
    Activations Density 0.012%

    No Known Activations