© 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
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 6-RES-JB
    6. 10801
    Prev
    Next
    INDEX
    Explanations

    phrases related to destruction, tearing, or dismantling

    oai_token-act-pair · gpt-3.5-turbo

    references to the concept of "shredding" or breaking down entities, whether literally or metaphorically

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Ortiz
    -0.80
     Floor
    -0.73
    lda
    -0.71
     Luther
    -0.69
    iliary
    -0.69
     Kamp
    -0.68
     Ballard
    -0.68
     Lange
    -0.65
     Silva
    -0.65
    stown
    -0.64
    POSITIVE LOGITS
    ding
    1.43
    riter
    1.00
    natureconservancy
    0.98
    sburg
    0.96
    wcsstore
    0.93
    ded
    0.90
    ritten
    0.87
    bler
    0.84
    der
    0.83
    bling
    0.82
    Activations Density 0.050%

    No Known Activations