© 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. 0-RES-JB
    11. 14793
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to specific entities or products

    oai_token-act-pair · gpt-3.5-turbo

    references to RF (radio frequency) technology or related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    wine
    -0.77
    ðĿ
    -0.72
    Nar
    -0.70
     Nanto
    -0.69
     Columb
    -0.68
     Jal
    -0.68
    Greek
    -0.67
    gon
    -0.65
     wine
    -0.65
    minus
    -0.65
    POSITIVE LOGITS
    RF
    4.18
     RF
    3.22
    rf
    2.29
     LF
    1.47
     EE
    1.07
     interf
    1.02
     DF
    0.98
     HF
    0.96
    PF
    0.95
     Wireless
    0.93
    Activations Density 0.031%

    No Known Activations