© 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 EvalsExportsinterp-engineNEWAPI 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. 3-RES-JB
    11. 8624
    Prev
    Next
    INDEX
    Explanations

    technical terms related to computer processors

    oai_token-act-pair · gpt-3.5-turbo

    references to octopus-related terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Interstitial
    -1.06
    ACTED
    -0.87
     Limbaugh
    -0.78
    culosis
    -0.77
    ãģĦ
    -0.76
    adder
    -0.73
    HCR
    -0.69
     Towns
    -0.69
     Cause
    -0.68
    WAYS
    -0.68
    POSITIVE LOGITS
    opus
    1.27
    oct
    1.15
     oct
    1.10
    ober
    1.00
    agonal
    0.98
    uple
    0.96
    agon
    0.91
    acles
    0.91
    acle
    0.90
    agons
    0.84
    Activations Density 0.009%

    No Known Activations