© 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. 9-RES-JB
    11. 18651
    Prev
    Next
    INDEX
    Explanations

    phrases related to a specific subject or entity named "Rosetta"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the Rosetta spacecraft

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ORN
    -0.65
     Countdown
    -0.62
    ered
    -0.60
     Hunger
    -0.60
    ulhu
    -0.59
    redit
    -0.58
    ãĥ¼ãĥĨãĤ£
    -0.57
     Idle
    -0.56
     setback
    -0.56
     finance
    -0.56
    POSITIVE LOGITS
    coe
    1.32
    etta
    1.26
    alez
    1.09
    enthal
    1.07
    kies
    1.03
    ario
    1.02
    anne
    1.00
    acea
    0.99
    atom
    0.99
    lyn
    0.98
    Activations Density 0.033%

    No Known Activations