© 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. 4-RES-JB
    11. 7507
    Prev
    Next
    INDEX
    Explanations

    phrases related to a specific location named "Ell"

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific entity or individual named "Ell."

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

    No Comments

    Negative Logits
    ãĥ£
    -0.83
    ItemTracker
    -0.75
    ========
    -0.68
    KING
    -0.66
    SHARE
    -0.66
    oglu
    -0.65
    Charges
    -0.65
    EED
    -0.63
    CHAR
    -0.62
    SHIP
    -0.62
    POSITIVE LOGITS
    ipt
    1.27
    sworth
    1.08
    izabeth
    1.08
    inia
    0.99
    sburg
    0.97
    yss
    0.93
    igible
    0.93
    otes
    0.92
    enium
    0.91
    imore
    0.91
    Activations Density 0.009%

    No Known Activations