© 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. 20630
    Prev
    Next
    INDEX
    Explanations

    enumerated lists or steps

    oai_token-act-pair · gpt-3.5-turbo

    numerical rankings or lists presented in chronological or sequential order

    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
    ±
    -0.75
    anasia
    -0.70
    vas
    -0.66
    imeter
    -0.65
    hei
    -0.64
    tek
    -0.62
    ebus
    -0.60
    µ
    -0.59
    ulz
    -0.59
    conn
    -0.59
    POSITIVE LOGITS
     chronological
    0.89
    :-
    0.88
     listings
    0.88
     sorted
    0.87
     spoilers
    0.85
    *:
    0.83
     alphabet
    0.80
     bookmark
    0.76
     list
    0.75
     highlights
    0.75
    Activations Density 0.863%

    No Known Activations