© 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. 4456
    Prev
    Next
    INDEX
    Explanations

    references related to postal services

    oai_token-act-pair · gpt-3.5-turbo

    references to postal services and delivery systems

    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
     Qiao
    -0.84
     Flavoring
    -0.77
    aughs
    -0.73
    IBLE
    -0.72
    ggle
    -0.71
    ãĤ¤ãĥĪ
    -0.71
     WATCHED
    -0.67
    OTS
    -0.66
    ãĤ¼ãĤ¦ãĤ¹
    -0.66
    oved
    -0.66
    POSITIVE LOGITS
    gres
    1.34
    greSQL
    1.28
    mortem
    1.06
    doctoral
    1.02
    erity
    0.94
    traumatic
    0.92
    natal
    0.89
    modern
    0.88
    cards
    0.80
    secondary
    0.80
    Activations Density 0.017%

    No Known Activations