© 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. 4-RES-JB
    11. 18571
    Prev
    Next
    INDEX
    Explanations

    words related to postal services, such as 'post office' and 'posthumous'

    oai_token-act-pair · gpt-3.5-turbo

    terms related to postal services and posthumous events

    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
    ONSORED
    -0.67
     Mahjong
    -0.67
    OST
    -0.66
    Bit
    -0.63
    é¾
    -0.63
    irlf
    -0.62
     Larson
    -0.62
    amiya
    -0.60
    MAP
    -0.58
    ç¥ŀ
    -0.58
    POSITIVE LOGITS
    opausal
    0.91
    umatic
    0.83
    DragonMagazine
    0.81
    roleum
    0.80
    ocalyptic
    0.79
    lict
    0.77
    antage
    0.75
    ritic
    0.74
    zon
    0.68
    liction
    0.68
    Activations Density 0.086%

    No Known Activations