© 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. 21025
    Prev
    Next
    INDEX
    Explanations

    phrases mentioning an increase or a change in size or scope

    oai_token-act-pair · gpt-3.5-turbo

    expressions related to widening or narrowing gaps or differences

    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
    da
    -0.79
    د
    -0.66
    orically
    -0.65
    è¦ļéĨĴ
    -0.63
     Electronic
    -0.62
    ÃĤ
    -0.60
     Celeb
    -0.59
    rone
    -0.58
     Ultr
    -0.58
    ENT
    -0.57
    POSITIVE LOGITS
     widen
    1.12
     widening
    1.10
     widened
    1.01
    borough
    0.87
     deepen
    0.87
    olars
    0.83
    pread
    0.83
     wid
    0.83
     brid
    0.81
    amel
    0.80
    Activations Density 0.013%

    No Known Activations