© 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. 7-RES-JB
    11. 249
    Prev
    Next
    INDEX
    Explanations

    words related to geographic locations and entities like countries, states, schools, clubs, and organizations

    oai_token-act-pair · gpt-3.5-turbo

    references to geographical locations, organizations, and competitive entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    racuse
    -0.69
    abella
    -0.69
     roofs
    -0.66
    croft
    -0.62
    agnar
    -0.62
     chambers
    -0.62
    usalem
    -0.60
    peria
    -0.60
    »Ĵ
    -0.59
    ories
    -0.59
    POSITIVE LOGITS
     indeed
    0.93
     nonetheless
    0.84
     considering
    0.80
     compared
    0.77
     devoid
    0.73
     insofar
    0.73
     unto
    0.71
     attracting
    0.70
     consisting
    0.69
     riddled
    0.68
    Activations Density 0.292%

    No Known Activations