© 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. 11-RES-JB
    6. 1016
    Prev
    Next
    INDEX
    Explanations

    phrases related to technical specifications and hardware components

    oai_token-act-pair · gpt-3.5-turbo

    the usage of terms related to a specific technology or system represented by the letter 'M' followed by a number

    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
     Beg
    -0.65
     christ
    -0.62
     Cathy
    -0.61
     commons
    -0.61
     Vik
    -0.61
     Hath
    -0.60
     Cheryl
    -0.60
     Dull
    -0.59
     Lilly
    -0.59
     Sakuya
    -0.58
    POSITIVE LOGITS
    utation
    1.33
    aintain
    1.26
    apping
    1.25
    ovable
    1.23
    appings
    1.22
    ixture
    1.20
    antle
    1.19
    ounter
    1.18
    odes
    1.17
    apper
    1.15
    Activations Density 0.047%

    No Known Activations