© 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. 6-RES-JB
    11. 11554
    Prev
    Next
    INDEX
    Explanations

    mentions of geographical locations, especially those with the word "Falls" in them

    oai_token-act-pair · gpt-3.5-turbo

    references to geographic locations, particularly places with the word "Falls"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    anyahu
    -0.72
    mble
    -0.70
    rons
    -0.69
    oen
    -0.68
    edy
    -0.67
     Luther
    -0.65
    ech
    -0.65
    illary
    -0.64
     ende
    -0.63
    urally
    -0.62
    POSITIVE LOGITS
     Falls
    1.09
    dale
    0.83
    LEY
    0.77
     Gorge
    0.76
    ashtra
    0.76
    ujah
    0.73
    head
    0.72
    doms
    0.71
    burgh
    0.71
     Mall
    0.70
    Activations Density 0.014%

    No Known Activations