© 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. 16685
    Prev
    Next
    INDEX
    Explanations

    keywords related to news articles and claims

    oai_token-act-pair · gpt-3.5-turbo

    numerical values or measurements

    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
     manif
    -0.74
     challeng
    -0.73
     culminating
    -0.68
     whipped
    -0.66
     accelerating
    -0.66
     snowball
    -0.64
     newsp
    -0.64
     whipping
    -0.63
    spread
    -0.63
     manifold
    -0.63
    POSITIVE LOGITS
     ILCS
    1.05
    ¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯¯
    0.89
    74
    0.87
    66
    0.86
    79
    0.85
    69
    0.85
    81
    0.84
    61
    0.83
    00
    0.83
    63
    0.83
    Activations Density 0.137%

    No Known Activations