© 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. 11-RES-JB
    11. 7470
    Prev
    Next
    INDEX
    Explanations

    phrases containing the word "dri" along with a numerical value indicating the intensity of the word's association in the document

    oai_token-act-pair · gpt-3.5-turbo

    terms related to dryness or drought conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Handler
    -0.69
    ueller
    -0.67
    izophren
    -0.63
    RY
    -0.63
    ablishment
    -0.63
     denomin
    -0.61
    geist
    -0.60
    ORE
    -0.59
    DIR
    -0.58
    ylum
    -0.56
    POSITIVE LOGITS
    zzle
    1.05
    vable
    0.97
    terness
    0.80
    quet
    0.76
    zz
    0.76
    ety
    0.75
    teenth
    0.75
    cible
    0.73
    eways
    0.72
    vel
    0.71
    Activations Density 0.102%

    No Known Activations