© 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. 7-RES-JB
    11. 9897
    Prev
    Next
    INDEX
    Explanations

    phrases or words related to dragons

    oai_token-act-pair · gpt-3.5-turbo

    words related to "agon" and its variations, suggesting a focus on themes of struggle or conflict

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ples
    -0.92
    bered
    -0.82
    uctor
    -0.69
     respons
    -0.67
    pler
    -0.65
    ensional
    -0.65
    pled
    -0.65
    posium
    -0.64
    ©¶æ
    -0.64
    orah
    -0.64
    POSITIVE LOGITS
    naire
    1.15
    iola
    0.91
    ciating
    0.90
    xon
    0.89
    naires
    0.87
    ESE
    0.86
    illin
    0.83
    ous
    0.82
    ary
    0.81
    otine
    0.81
    Activations Density 0.060%

    No Known Activations