© 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. 3-RES-JB
    11. 15127
    Prev
    Next
    INDEX
    Explanations

    references to locations using postal abbreviations containing "NE"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of "NE," likely referring to a specific geographic location or designation

    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
    gerald
    -0.78
    trap
    -0.74
    loo
    -0.71
    acies
    -0.71
     bearer
    -0.68
    icient
    -0.68
    ornia
    -0.66
    deck
    -0.64
    indal
    -0.62
    raviolet
    -0.62
    POSITIVE LOGITS
    braska
    1.03
    VE
    0.99
    IGH
    0.93
    ITH
    0.87
    arest
    0.84
    VER
    0.84
    VEN
    0.83
    ISS
    0.83
    erd
    0.81
    UT
    0.81
    Activations Density 0.008%

    No Known Activations