© 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. 0-RES-JB
    11. 1265
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "current" followed by a number representing strength or status

    oai_token-act-pair · gpt-3.5-turbo

    references to the word "current."

    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
    amins
    -0.80
    zai
    -0.70
    inis
    -0.66
     Everywhere
    -0.65
    itars
    -0.65
    gob
    -0.64
    kr
    -0.63
    Fest
    -0.63
    ooth
    -0.63
    jah
    -0.63
    POSITIVE LOGITS
     current
    3.58
    current
    2.51
     Current
    2.35
    Current
    2.27
     currently
    1.65
     existing
    1.59
    URRENT
    1.57
     present
    1.53
     currents
    1.50
    currently
    1.47
    Activations Density 0.021%

    No Known Activations