© 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. 21216
    Prev
    Next
    INDEX
    Explanations

    phrases related to changes or improvements

    oai_token-act-pair · gpt-3.5-turbo

    terms related to transformation or improvement processes

    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
    enza
    -0.66
    emp
    -0.64
     [+
    -0.64
    \">
    -0.63
    tale
    -0.62
    anza
    -0.59
    Jr
    -0.59
    Sm
    -0.59
    staking
    -0.59
    PLIED
    -0.57
    POSITIVE LOGITS
    issance
    0.81
     rethink
    0.76
     restruct
    0.75
    undown
    0.74
     radically
    0.73
     rewrite
    0.71
     rejuven
    0.69
    naissance
    0.69
    afort
    0.68
     reinvent
    0.67
    Activations Density 0.176%

    No Known Activations