© 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. 9-RES-JB
    6. 3323
    Prev
    Next
    INDEX
    Explanations

    locations and places such as cities and towns

    oai_token-act-pair · gpt-3.5-turbo

    specific geographical locations or places within a certain context

    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
    ICLE
    -0.75
    TIME
    -0.74
    ITION
    -0.73
    VICE
    -0.72
    ifact
    -0.71
    ODUCT
    -0.70
     actu
    -0.69
    oglobin
    -0.69
    ERA
    -0.68
    CEO
    -0.67
    POSITIVE LOGITS
     Highlands
    1.17
     Glen
    1.15
     Junction
    1.14
     Glou
    1.12
     Brunswick
    1.12
     Hills
    1.12
     Lake
    1.11
     Sussex
    1.10
     Alto
    1.09
     Lakes
    1.09
    Activations Density 0.202%

    No Known Activations