© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 11-RES-JB
    11. 14872
    Prev
    Next
    INDEX
    Explanations

    words or phrases related to a specific technical term, likely related to technology or a product feature, represented by the letter "T"

    oai_token-act-pair · gpt-3.5-turbo

    references to a specific product or brand denoted by the letter 'T'

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 11-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.11.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.11.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    11
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ment
    -0.70
     pseud
    -0.65
     Trib
    -0.61
     rounding
    -0.61
     thor
    -0.59
    theless
    -0.57
     sage
    -0.56
     Grac
    -0.56
     parts
    -0.56
     grooming
    -0.55
    POSITIVE LOGITS
    ribute
    1.41
    ARGET
    1.41
    akedown
    1.29
    olerance
    1.24
    ractor
    1.22
    ARDIS
    1.22
    rolley
    1.22
    oxicity
    1.21
    andem
    1.21
    URN
    1.19
    Activations Density 0.046%

    No Known Activations