© 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. 0-RES-JB
    11. 5350
    Prev
    Next
    INDEX
    Explanations

    phrases related to comparisons or relationships between different entities

    oai_token-act-pair · gpt-3.5-turbo

    references to relationships or comparisons between two entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 0-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.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.0.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    0
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    onom
    -0.68
    rison
    -0.64
    NAME
    -0.63
    ERSON
    -0.60
    ç¥ŀ
    -0.59
    Ħ¢
    -0.56
    Lear
    -0.54
    oran
    -0.54
    id
    -0.53
    vana
    -0.53
    POSITIVE LOGITS
     between
    3.30
    between
    3.02
     Between
    2.40
    Between
    1.97
     BET
    1.20
     separating
    1.20
     among
    1.12
     amongst
    1.11
     around
    0.96
     across
    0.94
    Activations Density 0.058%

    No Known Activations