© 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. 0-RES-JB
    11. 22378
    Prev
    Next
    INDEX
    Explanations

    terms related to the location "Aberdeen"

    oai_token-act-pair · gpt-3.5-turbo

    references to the place "Aberdeen."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ÏĦ
    -0.71
     Scroll
    -0.66
    itud
    -0.65
    atched
    -0.65
    HT
    -0.65
     sear
    -0.64
     epile
    -0.63
     Colt
    -0.62
     Vive
    -0.61
     transplant
    -0.61
    POSITIVE LOGITS
    deen
    3.90
     Aberdeen
    1.69
    din
    1.38
     Aber
    1.17
    die
    0.85
    sole
    0.82
    banks
    0.82
    anka
    0.78
    ded
    0.78
     Saber
    0.77
    Activations Density 0.031%

    No Known Activations