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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 8941
    Prev
    Next
    INDEX
    Explanations

    locations or places ending in 'abad'

    oai_token-act-pair · gpt-3.5-turbo

    mentions of specific geographical locations, particularly cities

    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
    avery
    -0.81
    zanne
    -0.67
     Ago
    -0.67
    PLAY
    -0.64
     Lauder
    -0.63
     Stim
    -0.62
     FANT
    -0.62
     PROG
    -0.60
     Plat
    -0.59
     replay
    -0.58
    POSITIVE LOGITS
    abad
    1.28
    pour
    0.95
    hai
    0.92
    adesh
    0.81
    uddin
    0.81
    rador
    0.81
    yrinth
    0.80
    umbai
    0.80
    culosis
    0.80
    ccoli
    0.78
    Activations Density 0.006%

    No Known Activations