Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 8-RES-JB
    6. 20542
    Prev
    Next
    INDEX
    Explanations

    terms related to criminal activities and organizations, particularly gangs

    oai_token-act-pair · gpt-3.5-turbo

    references to gang-related activities and violence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 8-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.8.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.8.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    8
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    etsk
    -0.82
    hower
    -0.76
    OPLE
    -0.74
     concess
    -0.70
    */(
    -0.68
    DonaldTrump
    -0.66
    ŃĶ
    -0.64
    andum
    -0.64
    pring
    -0.64
    issan
    -0.63
    POSITIVE LOGITS
    sta
    1.36
    ster
    1.25
    sters
    1.24
    busters
    1.23
    bang
    1.21
    rene
    1.06
    members
    1.01
    regate
    0.93
    member
    0.90
    buster
    0.88
    Activations Density 0.027%

    No Known Activations