© 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. 3-RES-JB
    6. 6196
    Prev
    Next
    INDEX
    Explanations

    mentions of tycoons and related terms

    oai_token-act-pair · gpt-3.5-turbo

    references to business tycoons

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 3-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.3.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.3.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    3
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ajor
    -0.93
    STD
    -0.81
    ECD
    -0.80
    stellar
    -0.74
    ãģ®éŃĶ
    -0.74
    ACTED
    -0.73
    é¾įåĸļ士
    -0.72
    HCR
    -0.71
    )=(
    -0.70
    anchester
    -0.70
    POSITIVE LOGITS
    coon
    1.34
     ty
    1.24
    rants
    0.84
    pos
    0.83
    rell
    0.82
    riter
    0.82
    oshenko
    0.80
    cor
    0.75
    ree
    0.74
    fing
    0.73
    Activations Density 0.006%

    No Known Activations