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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 14285
    Prev
    Next
    INDEX
    Explanations

    descriptions and details related to ladders and support structures

    oai_token-act-pair · gpt-3.5-turbo

    descriptions of various types of ladders and their features

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    ologne
    -0.93
     Stranger
    -0.85
    justice
    -0.78
     Violence
    -0.78
    acea
    -0.77
     Trends
    -0.77
     Vanessa
    -0.76
     Lyft
    -0.76
    profits
    -0.76
     Shame
    -0.75
    POSITIVE LOGITS
     cyl
    1.42
     rectangular
    1.40
     diameter
    1.28
     triangular
    1.27
     telesc
    1.26
     horizontally
    1.25
     vertically
    1.24
     mounted
    1.21
     perpendicular
    1.17
     adjustable
    1.17
    Activations Density 0.407%

    No Known Activations