© 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. 6-RES-JB
    11. 9649
    Prev
    Next
    INDEX
    Explanations

    instances of the word "alone" accompanied by contextual information about a person or group

    oai_token-act-pair · gpt-3.5-turbo

    references to individuals or entities that are not alone in their actions or circumstances

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    imize
    -0.76
    obal
    -0.73
    imate
    -0.73
    bern
    -0.65
    ewater
    -0.64
     respectively
    -0.62
    eer
    -0.62
    achment
    -0.59
    raviolet
    -0.59
    arov
    -0.59
    POSITIVE LOGITS
    ATA
    0.85
    NPR
    0.74
    Compl
    0.71
    WT
    0.71
     traged
    0.70
    ingen
    0.68
     contentious
    0.68
    atche
    0.67
     controversies
    0.67
    è¦ļéĨĴ
    0.66
    Activations Density 0.172%

    No Known Activations