© 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. 1-RES-JB
    11. 12950
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to locations, particularly cities

    oai_token-act-pair · gpt-3.5-turbo

    geographical locations, particularly cities or places with 'land' in their names

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 1-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.1.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.1.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    1
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    adem
    -0.82
    ads
    -0.74
    dn
    -0.74
    ks
    -0.73
    utor
    -0.72
    ad
    -0.70
    roman
    -0.70
    course
    -0.68
    cephal
    -0.68
    utch
    -0.68
    POSITIVE LOGITS
    LAND
    1.42
    STON
    1.33
    INGTON
    1.25
    VILLE
    1.24
    HEAD
    1.24
     IMAGES
    1.24
    COL
    1.22
    INE
    1.22
    CLASSIFIED
    1.21
    ANCE
    1.20
    Activations Density 0.045%

    No Known Activations