© 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. 4-RES-JB
    11. 6958
    Prev
    Next
    INDEX
    Explanations

    phrases related to expenses or costs

    oai_token-act-pair · gpt-3.5-turbo

    references to associated topics or issues

    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
    IVER
    -0.76
    UGE
    -0.74
    \\\\\\\\
    -0.74
    ifter
    -0.73
    OCK
    -0.72
    ardless
    -0.72
     Stras
    -0.69
    âķIJ
    -0.69
    ARD
    -0.68
     Trees
    -0.68
    POSITIVE LOGITS
     unrelated
    0.84
     thereto
    0.82
    worldly
    0.81
     newsp
    0.79
    paren
    0.79
    ness
    0.79
     activ
    0.78
    related
    0.78
     reconc
    0.77
     related
    0.77
    Activations Density 0.021%

    No Known Activations