© 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. 10-RES-JB
    11. 2684
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to geographical locations and organizations

    oai_token-act-pair · gpt-3.5-turbo

    mentions of geographical locations and related identifiers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    orer
    -0.73
    geist
    -0.70
    itiz
    -0.66
    rices
    -0.66
    zzle
    -0.65
    abase
    -0.64
    emonic
    -0.64
    thood
    -0.64
    olitan
    -0.64
    omic
    -0.63
    POSITIVE LOGITS
    VILLE
    1.50
    LAND
    1.40
    FIELD
    1.37
    TON
    1.37
     COUNTY
    1.36
    BUR
    1.34
    WOOD
    1.33
    STON
    1.30
     PARK
    1.30
    VIEW
    1.27
    Activations Density 0.085%

    No Known Activations