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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 3-RES-JB
    6. 1259
    Prev
    Next
    INDEX
    Explanations

    geographical locations, with a focus on the United Kingdom (UK)

    oai_token-act-pair · gpt-3.5-turbo

    references to the UK and related identifiers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tons
    -0.71
    chin
    -0.71
    issance
    -0.65
    lers
    -0.64
     Steps
    -0.64
    bryce
    -0.64
    rooms
    -0.63
    rums
    -0.63
    nea
    -0.63
    ¯¯¯¯
    -0.62
    POSITIVE LOGITS
    UGE
    0.96
    ERAL
    0.92
    yip
    0.88
    ATER
    0.83
    ESCO
    0.82
    MAP
    0.80
    KY
    0.80
    HI
    0.79
    DEV
    0.78
    AZ
    0.77
    Activations Density 0.017%

    No Known Activations