© 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. 9-RES-JB
    11. 20008
    Prev
    Next
    INDEX
    Explanations

    locations or settings within a text

    oai_token-act-pair · gpt-3.5-turbo

    phrases referencing specific locations or states

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    76561
    -0.86
     tyr
    -0.69
    ued
    -0.65
    oldown
    -0.62
    TED
    -0.62
     sshd
    -0.61
    _-
    -0.60
    emo
    -0.60
    ting
    -0.60
    Characters
    -0.60
    POSITIVE LOGITS
     ours
    0.72
    order
    0.67
    arest
    0.66
    abase
    0.66
     Appalach
    0.66
     Concord
    0.63
     America
    0.62
     DIY
    0.61
     Kitchen
    0.60
     home
    0.60
    Activations Density 0.099%

    No Known Activations