© 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. 2-RES-JB
    11. 17656
    Prev
    Next
    INDEX
    Explanations

    locations or positions within a text

    oai_token-act-pair · gpt-3.5-turbo

    references to locations or place names

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ħĭ
    -0.73
    deen
    -0.72
    RAW
    -0.66
     Thousand
    -0.66
    IELD
    -0.66
    graduate
    -0.64
     Ended
    -0.63
    FactoryReloaded
    -0.63
    PDATE
    -0.63
    Ô
    -0.62
    POSITIVE LOGITS
     loc
    1.25
    ator
    1.13
    ators
    1.02
    itud
    0.92
    iously
    0.87
    us
    0.87
    ational
    0.87
    uating
    0.81
    inia
    0.79
    ger
    0.79
    Activations Density 0.010%

    No Known Activations