© 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. 10-RES-JB
    11. 6895
    Prev
    Next
    INDEX
    Explanations

    words related to locations or place names, specifically focusing on names containing the letters 'ew'

    oai_token-act-pair · gpt-3.5-turbo

    specific geographical locations and their related entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     crunch
    -0.72
     embargo
    -0.68
    ãĥ¼ãĥĨ
    -0.67
     compan
    -0.66
    ij士
    -0.66
    ãĥĥãĥī
    -0.63
    -+-+
    -0.61
     artif
    -0.61
     parentheses
    -0.61
     rare
    -0.60
    POSITIVE LOGITS
    nesday
    1.05
    wo
    0.96
    lde
    0.91
    lich
    0.89
    kee
    0.89
    igans
    0.87
    owski
    0.87
    atche
    0.86
    ÅĤ
    0.86
    ingen
    0.84
    Activations Density 0.225%

    No Known Activations