© 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. 9-RES-JB
    11. 1030
    Prev
    Next
    INDEX
    Explanations

    phrases related to specific entities or topics, particularly "Antigua"

    oai_token-act-pair · gpt-3.5-turbo

    words and phrases related to "Antigua" and varying contexts surrounding it

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ĸļ
    -0.84
     envelope
    -0.67
     curtain
    -0.65
     envelop
    -0.64
    inki
    -0.64
     spheres
    -0.62
     paralle
    -0.60
    rely
    -0.60
     jewels
    -0.60
     veil
    -0.60
    POSITIVE LOGITS
    ctica
    0.96
    icrobial
    0.87
    ircraft
    0.77
    ravity
    0.76
    xiety
    0.73
    asio
    0.73
    heim
    0.72
    iotics
    0.72
    oppers
    0.72
    aban
    0.71
    Activations Density 0.092%

    No Known Activations