© 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. 3-RES-JB
    11. 10712
    Prev
    Next
    INDEX
    Explanations

    instances of the word "Dun" at varying levels of importance

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "Dun," indicative of geographic or personal references related to a specific location or individual

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    OHN
    -0.81
    NRS
    -0.72
    Magikarp
    -0.72
    âĸĪâĸĪ
    -0.69
    xual
    -0.68
    ORGE
    -0.62
     Tibetan
    -0.62
    anwhile
    -0.62
    ONS
    -0.61
    ãĥķãĤ©
    -0.60
    POSITIVE LOGITS
    wich
    1.01
    edin
    0.98
    querque
    0.98
    lap
    0.94
    agon
    0.94
    iet
    0.91
    wind
    0.89
    igan
    0.89
    leys
    0.88
    away
    0.88
    Activations Density 0.007%

    No Known Activations