© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 17181
    Prev
    Next
    INDEX
    Explanations

    references to locations, particularly focusing on places named "Long ____"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "Long" in a geographical context

    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
    ILA
    -0.77
    ADRA
    -0.75
    atically
    -0.68
    illions
    -0.68
    onomic
    -0.67
    ãĥ¯
    -0.67
    pecially
    -0.67
    代
    -0.66
    ħĭ
    -0.66
    æĺ
    -0.66
    POSITIVE LOGITS
    itudinal
    1.31
    er
    1.02
    itud
    0.98
    est
    0.97
    itude
    0.94
    shore
    0.91
    enhagen
    0.88
    leaf
    0.88
    sword
    0.87
    Strange
    0.81
    Activations Density 0.027%

    No Known Activations