© 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
    3. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    5. GPT2-Small
    7. Residual Stream
    9. 10-RES-JB
    11. 16090
    Prev
    Next
    INDEX
    Explanations

    instances of the term "In addition to" to highlight additional information or actions beyond what is already specified

    oai_token-act-pair · gpt-3.5-turbo

    the phrase "in addition" and its variations indicating supplementary information

    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
    ggles
    -0.70
    bis
    -0.61
    venge
    -0.58
    \\\\\\\\
    -0.58
    anos
    -0.55
    cised
    -0.55
     blat
    -0.54
     Inher
    -0.52
    aah
    -0.52
     Founders
    -0.52
    POSITIVE LOGITS
     thereto
    1.20
     to
    1.11
     TO
    0.78
    to
    0.69
    ,
    0.67
    To
    0.67
     ot
    0.66
     To
    0.65
    ombat
    0.64
    ,.
    0.61
    Activations Density 0.027%

    No Known Activations