© 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. 12907
    Prev
    Next
    INDEX
    Explanations

    words related to criminal activities, especially gangs

    oai_token-act-pair · gpt-3.5-turbo

    references to gang-related activities

    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
    hower
    -0.76
    OPLE
    -0.75
    éĸ
    -0.74
    teness
    -0.71
    etsk
    -0.70
     concess
    -0.69
    */(
    -0.69
     Dame
    -0.68
     Pwr
    -0.66
    andum
    -0.66
    POSITIVE LOGITS
    sta
    1.24
    busters
    1.18
    sters
    1.14
    ster
    1.12
    bang
    1.09
    members
    0.95
    rene
    0.90
    regate
    0.88
    atown
    0.86
    buster
    0.85
    Activations Density 0.023%

    No Known Activations