© 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. 2-RES-JB
    11. 23354
    Prev
    Next
    INDEX
    Explanations

    phrases related to the location "Dunedin"

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the name "Dun" or variations of it

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Magikarp
    -0.80
    OHN
    -0.76
    âĸĪâĸĪ
    -0.73
    xual
    -0.67
    ãĥķãĤ©
    -0.64
    76561
    -0.64
    NRS
    -0.63
     Prevent
    -0.63
     Robots
    -0.63
     Proposition
    -0.63
    POSITIVE LOGITS
    wich
    1.07
    edin
    0.96
    querque
    0.96
    lap
    0.93
    leigh
    0.92
    iac
    0.90
    leys
    0.90
    cair
    0.88
    igan
    0.87
    rib
    0.87
    Activations Density 0.009%

    No Known Activations