© 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. 2-RES-JB
    6. 17209
    Prev
    Next
    INDEX
    Explanations

    terms related to multiple or varied characteristics or factors

    oai_token-act-pair · gpt-3.5-turbo

    the occurrence of the prefix "mult" indicating multiplicity or diversity

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 2-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.2.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.2.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    2
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    HOME
    -0.84
    OPLE
    -0.82
    å§«
    -0.77
    Ö¼
    -0.75
    utenant
    -0.73
    âķIJ
    -0.72
    士
    -0.71
     Tigers
    -0.71
     Armory
    -0.70
    çͰ
    -0.70
    POSITIVE LOGITS
    icol
    1.31
    ilingual
    1.18
    ivariate
    1.17
    ivari
    1.10
    ipl
    1.07
    itud
    1.06
    iversal
    1.05
    iques
    1.02
    ilateral
    1.02
    amorph
    1.02
    Activations Density 0.006%

    No Known Activations