© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 8185
    Prev
    Next
    INDEX
    Explanations

    terms related to the contemporary time frame or current circumstances

    oai_token-act-pair · gpt-3.5-turbo

    references to the term "present" in various contexts

    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
    acid
    -0.67
    ryu
    -0.65
    rules
    -0.64
    ihad
    -0.64
    gob
    -0.63
    ospace
    -0.63
    Web
    -0.62
    anned
    -0.62
    rights
    -0.60
    LOCK
    -0.60
    POSITIVE LOGITS
     present
    3.97
    present
    2.74
     Present
    2.57
    Present
    2.30
     presents
    1.60
     current
    1.33
     presented
    1.21
     presenting
    1.21
     absent
    1.19
     PRES
    1.16
    Activations Density 0.018%

    No Known Activations