© 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. 6-RES-JB
    11. 20684
    Prev
    Next
    INDEX
    Explanations

    word forms and phrases of the term "crack"

    oai_token-act-pair · gpt-3.5-turbo

    references to the term "crack."

    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
    ikk
    -0.84
     Leth
    -0.72
    velength
    -0.69
    isted
    -0.68
     Pwr
    -0.67
    folk
    -0.67
     Fenrir
    -0.65
     Jinn
    -0.65
     Graveyard
    -0.65
    istic
    -0.64
    POSITIVE LOGITS
    pots
    1.13
    Berry
    1.04
    lings
    0.95
    pot
    0.93
    ible
    0.87
    ling
    0.86
    buster
    0.86
     cocaine
    0.84
    er
    0.83
    downs
    0.82
    Activations Density 0.022%

    No Known Activations