© 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. 20424
    Prev
    Next
    INDEX
    Explanations

    terms related to military equipment and operations

    oai_token-act-pair · gpt-3.5-turbo

    nouns and terms associated with various forms of media and analysis

    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
    Recomm
    -0.58
    Lear
    -0.55
    Said
    -0.54
    Translation
    -0.51
    laughs
    -0.49
    amaz
    -0.49
     Friendly
    -0.48
    tains
    -0.47
    hands
    -0.46
    Repl
    -0.46
    POSITIVE LOGITS
     are
    1.39
     aren
    1.27
     seem
    1.26
     have
    1.25
     tend
    1.24
     comprise
    1.21
     abound
    1.18
     appear
    1.14
     deserve
    1.14
     constitute
    1.13
    Activations Density 0.568%

    No Known Activations