© 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. 7-RES-JB
    11. 16726
    Prev
    Next
    INDEX
    Explanations

    locations or place names related to cities in Wales

    oai_token-act-pair · gpt-3.5-turbo

    references to places and entities in Wales, particularly Cardiff and Swansea

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    eering
    -1.01
    ĸļ
    -1.00
    nels
    -0.92
    ramid
    -0.74
    ographed
    -0.74
    eers
    -0.74
    hammad
    -0.71
    orter
    -0.71
    lique
    -0.70
    eki
    -0.68
    POSITIVE LOGITS
     Cardiff
    0.89
     Wales
    0.82
    yard
    0.78
     Davies
    0.76
     Welsh
    0.76
     Bale
    0.73
    reath
    0.71
    mere
    0.71
    ford
    0.70
    pool
    0.70
    Activations Density 0.055%

    No Known Activations