© 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. 8-RES-JB
    11. 9445
    Prev
    Next
    INDEX
    Explanations

    references to locations, particularly related to New York (NY)

    oai_token-act-pair · gpt-3.5-turbo

    mentions of New York and New Jersey

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iasis
    -0.80
    abase
    -0.71
    naire
    -0.70
    wagen
    -0.69
     Notting
    -0.65
    tenance
    -0.65
    framework
    -0.64
     Danish
    -0.64
    toggle
    -0.63
    baugh
    -0.63
    POSITIVE LOGITS
    CHR
    1.25
    RA
    1.18
    FW
    1.17
    OTUS
    1.16
    FR
    1.15
    TO
    1.14
    BI
    1.13
    OF
    1.12
    RB
    1.12
    OC
    1.12
    Activations Density 0.072%

    No Known Activations