© 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. 10-RES-JB
    6. 12483
    Prev
    Next
    INDEX
    Explanations

    phrases involving the word 'reduction'

    oai_token-act-pair · gpt-3.5-turbo

    occurrences of the prefix "eg," indicating a focus on specific references or categorizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 10-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.10.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.10.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    10
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ãĥ´ãĤ¡
    -0.73
    ãĥīãĥ©ãĤ´ãĥ³
    -0.67
    éĹĺ
    -0.64
     Franch
    -0.64
     Tsu
    -0.64
     naughty
    -0.63
     Wicked
    -0.62
    GMT
    -0.60
     è£ı
    -0.58
    DERR
    -0.57
    POSITIVE LOGITS
    asus
    1.27
    raphics
    1.21
    uild
    1.08
    entric
    1.07
    regate
    1.06
    lasses
    1.03
    ardless
    1.02
    rowth
    1.02
    otiation
    0.98
    hetto
    0.98
    Activations Density 0.030%

    No Known Activations