© 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. 4-RES-JB
    11. 14681
    Prev
    Next
    INDEX
    Explanations

    sequences of characters that correspond to a specific formatting in a document

    oai_token-act-pair · gpt-3.5-turbo

    references to direct communication or connection

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

    No Comments

    Negative Logits
     agre
    -0.87
     destro
    -0.78
     Strongh
    -0.73
    hement
    -0.72
     streng
    -0.71
     veter
    -0.67
     oun
    -0.66
     honoured
    -0.66
     entrenched
    -0.65
     trump
    -0.64
    POSITIVE LOGITS
    ////////////////////////////////
    1.02
    Posts
    0.96
    Minecraft
    0.93
    Joined
    0.93
    ================================================================
    0.93
    Topics
    0.92
    ========
    0.92
    Reply
    0.92
    Associated
    0.91
    --------------------
    0.90
    Activations Density 0.365%

    No Known Activations