© 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. 1-RES-JB
    6. 7619
    Prev
    Next
    INDEX
    Explanations

    the name "Marcus" in different contexts or sentences

    oai_token-act-pair · gpt-3.5-turbo

    references to the name "Marcus."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ebook
    -0.79
    boarding
    -0.77
    eared
    -0.76
    ships
    -0.74
    saf
    -0.69
    eer
    -0.66
    eering
    -0.66
    comes
    -0.65
    ende
    -0.65
    Ĥª
    -0.64
    POSITIVE LOGITS
    Marcus
    1.33
     Aure
    1.21
     Marcus
    1.07
    ias
    0.84
    ius
    0.83
     Mari
    0.79
    bryce
    0.78
     Isa
    0.78
     Curtis
    0.75
     Malfoy
    0.75
    Activations Density 0.009%

    No Known Activations