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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 9-RES-JB
    11. 4193
    Prev
    Next
    INDEX
    Explanations

    prepositions followed by specific location indicators

    oai_token-act-pair · gpt-3.5-turbo
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 9-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.9.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.9.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    9
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    OWS
    -0.85
    quickShipAvailable
    -0.72
    VERTISEMENT
    -0.68
    ĪĴ
    -0.64
    omer
    -0.63
     Alone
    -0.62
    ĵ
    -0.62
    catentry
    -0.62
    lement
    -0.61
    ember
    -0.61
    POSITIVE LOGITS
     nowhere
    0.89
     here
    0.87
     somew
    0.83
     existence
    0.83
     somewhere
    0.78
     sight
    0.75
    between
    0.74
     heaven
    0.74
     abundance
    0.73
    itialized
    0.71
    Activations Density 0.233%

    No Known Activations