© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 1-RES-JB
    11. 21361
    Prev
    Next
    INDEX
    Explanations

    phrases related to specific characters or locations with particular characters

    oai_token-act-pair · gpt-3.5-turbo

    sequences of special characters or symbols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     interf
    -0.81
     mutually
    -0.75
     strained
    -0.75
     tentative
    -0.74
     unex
    -0.73
     undercover
    -0.73
     confidentiality
    -0.69
     confidential
    -0.68
     unpaid
    -0.68
     critically
    -0.68
    POSITIVE LOGITS
    =#
    1.20
    Į
    1.19
    «
    1.01
    âĶĢâĶĢâĶĢâĶĢ
    0.99
    ĥ
    0.97
    ¨
    0.94
     ÙĪ
    0.93
    IJ
    0.92
    ÙĨ
    0.91
    åŃIJ
    0.91
    Activations Density 0.006%

    No Known Activations