© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 2-RES-JB
    11. 7624
    Prev
    Next
    INDEX
    Explanations

    terms related to what remains or is left behind after something has been removed or used

    oai_token-act-pair · gpt-3.5-turbo

    terms related to remnants or leftover entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    thood
    -0.83
    otom
    -0.77
    GO
    -0.71
    imb
    -0.71
    annis
    -0.69
    itals
    -0.69
    orth
    -0.68
     instantaneous
    -0.68
    sych
    -0.67
    justice
    -0.66
    POSITIVE LOGITS
     remnants
    1.41
     leftover
    1.00
     remnant
    0.97
     traces
    0.95
     ashes
    0.92
     residual
    0.91
     residue
    0.87
     residues
    0.82
    nants
    0.79
     scraps
    0.77
    Activations Density 0.019%

    No Known Activations