© 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. 3663
    Prev
    Next
    INDEX
    Explanations

    specific characters used as markers or indicators

    oai_token-act-pair · gpt-3.5-turbo

    instances of certain non-standard characters or symbols

    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
     buggy
    -0.75
     decomp
    -0.74
     collecting
    -0.74
     coast
    -0.73
     minim
    -0.73
     capsule
    -0.72
     floating
    -0.69
     downs
    -0.68
    itably
    -0.68
     shrouded
    -0.68
    POSITIVE LOGITS
    ONSORED
    0.99
    £
    0.98
    ¹
    0.87
    ĸļ
    0.86
    ł
    0.86
     Ibid
    0.83
    º
    0.80
    catentry
    0.80
    Order
    0.80
    ¯
    0.80
    Activations Density 0.209%

    No Known Activations