© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 3-RES-JB
    11. 13632
    Prev
    Next
    INDEX
    Explanations

    phrases related to specific locations or entities, especially ones related to "Forest Hills."

    oai_token-act-pair · gpt-3.5-turbo

    references to forests and related geographical locations

    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
    esthetic
    -0.73
    demand
    -0.71
    verages
    -0.70
    soever
    -0.69
     observable
    -0.65
    DonaldTrump
    -0.65
    selves
    -0.64
    ifice
    -0.62
    atform
    -0.62
    interstitial
    -0.62
    POSITIVE LOGITS
     Forest
    1.03
    Forest
    0.93
    lands
    0.89
    land
    0.87
    lake
    0.87
     Lawn
    0.83
    ieri
    0.80
     Hills
    0.79
     Valley
    0.79
     Park
    0.78
    Activations Density 0.007%

    No Known Activations