© 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. 4052
    Prev
    Next
    INDEX
    Explanations

    words related to sandy environments and materials

    oai_token-act-pair · gpt-3.5-turbo

    references to sand

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    ostics
    -0.76
    otine
    -0.69
     aver
    -0.65
    asio
    -0.62
    ENCE
    -0.62
    ISE
    -0.62
    士
    -0.62
    IGH
    -0.60
    istics
    -0.60
    iren
    -0.59
    POSITIVE LOGITS
    castle
    1.10
    bags
    1.06
    bag
    0.99
    stone
    0.97
    paper
    0.93
    hill
    0.91
    aled
    0.87
    als
    0.86
    tro
    0.85
    storms
    0.85
    Activations Density 0.040%

    No Known Activations