© 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. 4-RES-JB
    11. 10446
    Prev
    Next
    INDEX
    Explanations

    references to a specific company or brand named "Essar"

    oai_token-act-pair · gpt-3.5-turbo

    mentions of the word "Ess" and related terms in various contexts

    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
     sight
    -0.74
    è¦ļéĨĴ
    -0.72
    ãĥ£
    -0.64
    faced
    -0.64
    EStream
    -0.61
    hyde
    -0.61
    trl
    -0.61
    population
    -0.61
    SPONSORED
    -0.61
    SHARE
    -0.60
    POSITIVE LOGITS
    entials
    1.50
    endon
    1.32
    ences
    1.13
    ential
    1.06
    entially
    1.03
    inite
    1.02
    ensible
    1.00
    gard
    0.93
    aults
    0.92
    ues
    0.91
    Activations Density 0.006%

    No Known Activations