© 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. 2730
    Prev
    Next
    INDEX
    Explanations

    instances of the word "Multipath"

    oai_token-act-pair · gpt-3.5-turbo

    references to the term "Mult" related to digital systems or technology

    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
     Lilly
    -0.73
     defect
    -0.72
     shady
    -0.72
    issions
    -0.72
    sei
    -0.71
    insk
    -0.70
    natureconservancy
    -0.67
    gey
    -0.67
    phies
    -0.66
    iane
    -0.65
    POSITIVE LOGITS
     Mult
    3.48
    Mult
    3.14
    mult
    2.42
     Multi
    1.79
    Multi
    1.53
     multic
    1.45
     mult
    1.37
     multip
    1.36
     multit
    1.33
     Ampl
    1.29
    Activations Density 0.025%

    No Known Activations