© 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. 4-RES-JB
    11. 24186
    Prev
    Next
    INDEX
    Explanations

    words related to a specific name "Dur" or "Duran"

    oai_token-act-pair · gpt-3.5-turbo

    instances of the name "Dur" and its various forms

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

    No Comments

    Negative Logits
    NetMessage
    -0.96
    ħĭ
    -0.79
    76561
    -0.72
    insula
    -0.70
     Simulator
    -0.69
     Panic
    -0.69
    pocket
    -0.65
    REDACTED
    -0.63
    xual
    -0.62
    pard
    -0.62
    POSITIVE LOGITS
     Dur
    0.95
    locks
    0.88
    lock
    0.87
    anty
    0.87
    rell
    0.86
    ably
    0.84
    nit
    0.83
    abl
    0.82
    rence
    0.81
    rington
    0.80
    Activations Density 0.012%

    No Known Activations