© 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 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. 8-RES-JB
    11. 19418
    Prev
    Next
    INDEX
    Explanations

    references to the name "Sand" with varying numerical values

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the name "Sand" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    urses
    -0.79
     sight
    -0.78
    uates
    -0.77
    UTERS
    -0.72
     lockout
    -0.67
     toxin
    -0.66
    KT
    -0.64
    verages
    -0.64
     pity
    -0.64
     polarization
    -0.61
    POSITIVE LOGITS
    wic
    1.29
    oval
    1.12
    usky
    1.08
    alph
    1.07
    hill
    0.98
    paper
    0.95
    boxing
    0.94
    hya
    0.94
    erson
    0.93
    box
    0.93
    Activations Density 0.028%

    No Known Activations