© 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. 8869
    Prev
    Next
    INDEX
    Explanations

    references to a particular software or gaming platform called "Epic."

    oai_token-act-pair · gpt-3.5-turbo

    references to the term "Epic" and its 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
    creen
    -0.86
    SPONSORED
    -0.76
    à©
    -0.73
    ³³³³³³³³³³³³³³³³
    -0.68
    wark
    -0.68
    ÏĤ
    -0.67
    ****************
    -0.65
    Downloadha
    -0.64
    Ùİ
    -0.64
    folk
    -0.64
    POSITIVE LOGITS
    enter
    1.11
    urious
    0.97
    urus
    0.83
    ension
    0.82
    rament
    0.80
    ulously
    0.78
    rous
    0.77
    Draft
    0.76
    ensions
    0.74
    ocratic
    0.72
    Activations Density 0.007%

    No Known Activations