© 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. 8-RES-JB
    11. 3402
    Prev
    Next
    INDEX
    Explanations

    phrases related to specific actions or tasks

    oai_token-act-pair · gpt-3.5-turbo

    elements related to structured data and functionalities in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    xual
    -0.81
     undecided
    -0.80
     neighb
    -0.78
     favor
    -0.77
     este
    -0.71
     grip
    -0.71
     prosec
    -0.71
     scrap
    -0.69
     grop
    -0.69
     therap
    -0.69
    POSITIVE LOGITS
    Its
    1.58
    However
    1.53
    Because
    1.52
    Since
    1.52
    Specifically
    1.50
    It
    1.47
    That
    1.47
    Why
    1.47
    Therefore
    1.47
    But
    1.46
    Activations Density 0.533%

    No Known Activations