© 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. 549
    Prev
    Next
    INDEX
    Explanations

    ordinal numbers indicating a ranking position among a group

    oai_token-act-pair · gpt-3.5-turbo

    rankings or ordinal positions of entities

    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
    ocations
    -0.63
     conver
    -0.63
     Migration
    -0.61
     energies
    -0.61
     interf
    -0.60
     pilgrims
    -0.60
     imb
    -0.59
     reprint
    -0.59
    ACTION
    -0.59
     brim
    -0.58
    POSITIVE LOGITS
    retty
    0.78
    ranked
    0.76
    govtrack
    0.75
     Runner
    0.75
     baseman
    0.74
    illac
    0.74
    BuyableInstoreAndOnline
    0.71
    oof
    0.70
    arily
    0.70
     ..........
    0.70
    Activations Density 0.057%

    No Known Activations