© 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. 6-RES-JB
    11. 8234
    Prev
    Next
    INDEX
    Explanations

    phrases related to numbers or mathematical expressions

    oai_token-act-pair · gpt-3.5-turbo

    special characters or punctuation marks

    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
    ally
    -0.68
    doors
    -0.65
     disadvant
    -0.61
    enhagen
    -0.60
     exha
    -0.59
     toes
    -0.58
     blasphemy
    -0.58
     vulner
    -0.58
     generals
    -0.58
    iani
    -0.57
    POSITIVE LOGITS
    actionDate
    0.74
    mosp
    0.73
     partName
    0.69
     Psy
    0.67
    taboola
    0.65
    nee
    0.64
     ][
    0.63
    hov
    0.63
    ead
    0.59
    CLUS
    0.58
    Activations Density 0.062%

    No Known Activations