© 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. 2-RES-JB
    11. 8336
    Prev
    Next
    INDEX
    Explanations

    mentions of the name "Ric" with varying intensities

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Anchorage
    -0.80
     Parenthood
    -0.75
    ITNESS
    -0.74
    ulhu
    -0.72
    skirts
    -0.71
    uyomi
    -0.71
     Terminal
    -0.71
    é¾
    -0.70
     Kinnikuman
    -0.69
    ãģĨ
    -0.69
    POSITIVE LOGITS
    ochet
    1.28
    otine
    1.06
     Ric
    1.02
    helle
    0.90
    asso
    0.88
    otti
    0.85
    otta
    0.84
    eny
    0.83
    zon
    0.80
    afort
    0.80
    Activations Density 0.004%

    No Known Activations