© 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. 3-RES-JB
    6. 13346
    Prev
    Next
    INDEX
    Explanations

    names related to a particular entity "Musqueam"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "Mus" in various contexts, likely indicating a focus on specific musical or cultural references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Yamato
    -0.75
     EDITION
    -0.72
    etheless
    -0.72
     Aval
    -0.70
     Breach
    -0.69
     bye
    -0.67
     coli
    -0.66
     Sora
    -0.64
     Anaheim
    -0.64
     Highlander
    -0.63
    POSITIVE LOGITS
    icians
    1.11
    ificent
    1.10
    ician
    1.09
    ket
    1.02
    mus
    0.94
    cular
    0.94
    chet
    0.93
    natureconservancy
    0.93
    cles
    0.92
    ique
    0.90
    Activations Density 0.007%

    No Known Activations