© 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. 10-RES-JB
    11. 2642
    Prev
    Next
    INDEX
    Explanations

    special characters like 'Ċ' and numbers

    oai_token-act-pair · gpt-3.5-turbo

    references to gameplay mechanics and technical aspects of video games

    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
     flats
    -0.75
     Lug
    -0.69
     bandits
    -0.67
     Krypt
    -0.65
     Tag
    -0.64
     judgement
    -0.64
     glare
    -0.62
     Slug
    -0.62
     ageing
    -0.61
     Atomic
    -0.60
    POSITIVE LOGITS
    ³³³³³³³³³³³³³³³³
    1.14
    ³³³³³³³³
    1.00
    sonian
    0.98
    ³³³
    0.96
    ³³³³
    0.89
    bus
    0.87
    Bus
    0.86
    shall
    0.83
    colored
    0.83
    nature
    0.81
    Activations Density 0.100%

    No Known Activations