© 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. 21791
    Prev
    Next
    INDEX
    Explanations

    places such as mountains, streets, woods, and seas

    oai_token-act-pair · gpt-3.5-turbo

    geographical features, particularly mountains and streets

    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
    -+-+
    -0.67
    asus
    -0.62
    ASED
    -0.60
    izont
    -0.59
    nce
    -0.58
    --+
    -0.57
    Ī
    -0.57
    nia
    -0.57
    arus
    -0.57
    rosso
    -0.56
    POSITIVE LOGITS
    cape
    1.47
    pring
    1.29
    pace
    1.28
    creen
    1.26
    cale
    1.23
    chool
    1.21
    hip
    1.18
    paces
    1.17
    hare
    1.17
    hift
    1.16
    Activations Density 0.214%

    No Known Activations