Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 6-RES-JB
    6. 14328
    Prev
    Next
    INDEX
    Explanations

    cities or locations mentioned in news or articles

    oai_token-act-pair · gpt-3.5-turbo

    geographical locations and their names within the document

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    the region name in "[place], [region]"

    Explanation Uploaded by User
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ginx
    -0.63
    "},
    -0.63
    cycle
    -0.62
    "}
    -0.62
    anges
    -0.62
    case
    -0.59
    aea
    -0.58
    âĹ¼
    -0.57
    Shape
    -0.56
    Scope
    -0.56
    POSITIVE LOGITS
     POL
    0.83
     YORK
    0.70
    WASHINGTON
    0.68
     COUNTY
    0.67
     CITY
    0.65
     JUL
    0.64
     BALL
    0.63
     APR
    0.62
     Saud
    0.62
    zsche
    0.61
    Activations Density 0.072%

    No Known Activations