© 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. 9484
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a broad geographical or demographic scope, often related to global or nationwide involvement

    oai_token-act-pair · gpt-3.5-turbo

    references to inclusivity and diversity across various groups and regions

    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
    potion
    -0.86
     presumption
    -0.72
    pmwiki
    -0.72
    esson
    -0.67
    Proof
    -0.65
    ãĤº
    -0.64
    anting
    -0.62
     lest
    -0.59
    attribute
    -0.59
     fatigue
    -0.59
    POSITIVE LOGITS
     disciplines
    0.92
    abama
    0.81
     continents
    0.80
     Indies
    0.76
     faiths
    0.70
     denominations
    0.70
    iterranean
    0.69
     genders
    0.69
     sexes
    0.68
    pires
    0.68
    Activations Density 0.131%

    No Known Activations