Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 10-RES-JB
    6. 11981
    Prev
    Next
    INDEX
    Explanations

    mentions of technology and financial terms

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ipl
    -0.70
    iman
    -0.65
     Gors
    -0.62
     Helpful
    -0.57
    }.
    -0.57
    same
    -0.57
    itant
    -0.57
    irection
    -0.57
     "$:/
    -0.57
    omever
    -0.56
    POSITIVE LOGITS
     underwent
    1.15
     died
    1.09
     arrives
    1.08
     succumbed
    1.06
     debuted
    1.04
     collided
    1.03
     emerged
    1.02
     surfaced
    1.01
     celebrates
    1.01
     surged
    1.01
    Activations Density 0.559%

    No Known Activations