© 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. 14035
    Prev
    Next
    INDEX
    Explanations

    phrases introducing a list or enumeration

    oai_token-act-pair · gpt-3.5-turbo

    instances of the word "the" used in various contexts

    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
    hyde
    -0.73
    cycle
    -0.73
    oshop
    -0.73
    ACY
    -0.70
    HOME
    -0.70
    click
    -0.69
    fulness
    -0.68
    ago
    -0.68
    ynthesis
    -0.67
    ION
    -0.67
    POSITIVE LOGITS
     myriad
    1.05
     dozen
    1.01
     dozens
    0.99
     contenders
    0.97
     casualties
    0.93
     offerings
    0.93
     many
    0.90
     multitude
    0.89
     beneficiaries
    0.89
     brightest
    0.88
    Activations Density 0.136%

    No Known Activations