© 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. 4-RES-JB
    6. 10660
    Prev
    Next
    INDEX
    Explanations

    phrases related to joining a company or specific positions at a company

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the term "arc"

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

    No Comments

    Negative Logits
    fulness
    -0.89
    lihood
    -0.80
     à¤
    -0.77
    ãģŁ
    -0.75
    fficiency
    -0.70
    FUL
    -0.70
    tty
    -0.70
    tons
    -0.66
    mble
    -0.66
     Vive
    -0.65
    POSITIVE LOGITS
    otics
    1.08
    adian
    1.05
    adia
    0.96
    arc
    0.95
    asm
    0.95
    inia
    0.92
    aine
    0.92
    issa
    0.87
    itect
    0.86
    inates
    0.84
    Activations Density 0.012%

    No Known Activations