© 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. 1305
    Prev
    Next
    INDEX
    Explanations

    acronyms related to industries or organizations

    oai_token-act-pair · gpt-3.5-turbo

    specific abbreviations or acronyms related to various entities or topics

    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
    taboola
    -0.76
    gie
    -0.71
     glow
    -0.65
     conspicuous
    -0.65
    alam
    -0.64
    nard
    -0.62
    ighton
    -0.60
    scl
    -0.58
    ikarp
    -0.57
    olia
    -0.57
    POSITIVE LOGITS
    ATA
    1.21
    senal
    1.14
    OSS
    1.10
    AR
    1.10
    OPS
    1.10
    ARE
    1.07
    RA
    1.07
    TO
    1.05
    OP
    1.05
    ENE
    1.04
    Activations Density 0.194%

    No Known Activations