© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 2359
    Prev
    Next
    INDEX
    Explanations

    words or phrases related to the location "Durham" or "Police Chief Larry Smith."

    oai_token-act-pair · gpt-3.5-turbo

    repeated references to a specific location or establishment

    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
     Phar
    -0.60
     Pebble
    -0.60
     Span
    -0.58
     Sark
    -0.58
     Cruiser
    -0.58
    oslav
    -0.57
     Camel
    -0.57
     Bah
    -0.57
     Qing
    -0.57
    \\\\\\\\\\\\\\\\
    -0.56
    POSITIVE LOGITS
    istance
    1.38
    cue
    1.21
    idency
    1.17
    olutions
    1.11
    olver
    1.05
    pring
    1.04
    idence
    1.04
    cale
    1.03
    erve
    1.02
    pell
    1.02
    Activations Density 0.011%

    No Known Activations