© 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. 7-RES-JB
    11. 21141
    Prev
    Next
    INDEX
    Explanations

    references to physical objects or actions that can be touched or manipulated

    oai_token-act-pair · gpt-3.5-turbo

    specific nouns related to various themes or subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 7-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.7.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.7.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    7
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ascal
    -0.61
    anchester
    -0.59
    andem
    -0.59
    enza
    -0.59
    ilk
    -0.58
    reek
    -0.58
    Hay
    -0.56
    roma
    -0.54
    omez
    -0.54
    ahon
    -0.53
    POSITIVE LOGITS
    usercontent
    0.55
     reperto
    0.54
     experien
    0.54
     exhib
    0.54
    ãĤ¼ãĤ¦ãĤ¹
    0.54
    Materials
    0.54
    naires
    0.53
    dayName
    0.53
    EStream
    0.52
     externalToEVAOnly
    0.51
    Activations Density 0.621%

    No Known Activations