© 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. 6-RES-JB
    11. 15527
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a specific point in time or progress into an event or situation

    oai_token-act-pair · gpt-3.5-turbo

    phrases indicating progression or time intervals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 6-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.6.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.6.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    6
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    found
    -0.65
    club
    -0.64
    Tools
    -0.62
    MA
    -0.62
     NEC
    -0.61
     Inqu
    -0.60
     Wel
    -0.60
    wolf
    -0.60
    wolves
    -0.59
    ãĤ¦ãĤ¹
    -0.58
    POSITIVE LOGITS
    imester
    1.14
    ricular
    0.86
    avez
    0.74
    actionDate
    0.73
    uberty
    0.72
     âĶľ
    0.68
    ngth
    0.68
     hiber
    0.68
     adulthood
    0.68
     retirement
    0.67
    Activations Density 0.084%

    No Known Activations