© 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. 3-RES-JB
    11. 13388
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "mast" followed by numbers which likely refer to different occurrences or contexts

    oai_token-act-pair · gpt-3.5-turbo

    references to specific individuals or names along with terms related to masts and their associated contexts

    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
    Ô
    -0.82
    PsyNetMessage
    -0.79
    ppo
    -0.70
    efficients
    -0.68
    hift
    -0.66
    mble
    -0.66
    ITED
    -0.65
    DragonMagazine
    -0.65
    BOOK
    -0.65
    Madison
    -0.64
    POSITIVE LOGITS
    odon
    1.15
     mast
    1.14
    mast
    1.02
    icated
    0.90
    romancer
    0.88
    ication
    0.86
    rodu
    0.85
    roph
    0.83
    rament
    0.81
    ectomy
    0.77
    Activations Density 0.010%

    No Known Activations