© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 10-RES-JB
    6. 874
    Prev
    Next
    INDEX
    Explanations

    a specific character (Ċ) present in the text

    oai_token-act-pair · gpt-3.5-turbo

    instructions or guidelines related to processes

    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
     hosting
    -0.74
     freel
    -0.69
     diving
    -0.69
     rallying
    -0.67
     hashing
    -0.67
     doubling
    -0.65
     amnesty
    -0.65
     politic
    -0.63
    terday
    -0.63
     hackers
    -0.63
    POSITIVE LOGITS
    ³³³³³³³³³³³³³³³³
    1.30
    âĵĺ
    1.24
    ³³³³
    1.20
    ³³³³³³³³
    1.19
    Contents
    1.16
    Example
    1.14
    Ingredients
    1.13
    ³³³
    1.12
    ³³
    1.01
    RESULTS
    0.99
    Activations Density 0.307%

    No Known Activations