© 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. 11-RES-JB
    11. 17039
    Prev
    Next
    INDEX
    Explanations

    descriptive terms related to technical features or processes

    oai_token-act-pair · gpt-3.5-turbo

    terms related to organizational structures, protocols, and systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aughs
    -0.94
     Hits
    -0.89
    orns
    -0.88
     tragedies
    -0.84
    projects
    -0.83
    ittens
    -0.82
     fears
    -0.81
    axies
    -0.81
    ongs
    -0.80
    ooks
    -0.79
    POSITIVE LOGITS
     consisting
    1.22
     whereby
    1.15
     mechanism
    1.05
     solution
    1.03
     template
    0.99
     structure
    0.99
     scheme
    0.98
     comprising
    0.98
     layer
    0.96
     wherein
    0.95
    Activations Density 0.474%

    No Known Activations