© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 4-RES-JB
    11. 22198
    Prev
    Next
    INDEX
    Explanations

    comparisons between different things or situations

    oai_token-act-pair · gpt-3.5-turbo

    comparative phrases indicating preference or alternatives

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

    No Comments

    Negative Logits
    oret
    -0.61
     understatement
    -0.58
    itudinal
    -0.57
    hack
    -0.57
     Rah
    -0.57
    onom
    -0.57
    ãĤ®
    -0.56
    actic
    -0.56
    Pet
    -0.54
    mosp
    -0.54
    POSITIVE LOGITS
     thereby
    0.72
     respectively
    0.68
    hammad
    0.66
     disadvant
    0.64
    soever
    0.59
     favour
    0.58
     Thousand
    0.57
     undet
    0.57
     anywhere
    0.57
    İĭ
    0.57
    Activations Density 0.910%

    No Known Activations