© 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. 4-RES-JB
    11. 7131
    Prev
    Next
    INDEX
    Explanations

    terms relating to destruction or tearing into pieces

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of shredding, both literally and metaphorically

    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
    annis
    -0.76
    emis
    -0.63
    amide
    -0.62
    ioch
    -0.61
    juven
    -0.61
     presiding
    -0.61
     Ple
    -0.61
    EGA
    -0.61
     Gard
    -0.60
     Swords
    -0.60
    POSITIVE LOGITS
    ding
    1.37
     shred
    1.12
    aby
    1.01
    sburg
    0.97
    der
    0.97
    itionally
    0.94
    ulously
    0.93
    nuts
    0.90
    lings
    0.87
    ming
    0.87
    Activations Density 0.007%

    No Known Activations