INDEX

Explanations

phrases discussing cause and effect relationships or outcomes

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 snippetHide

-0.87

NewUrlParser

-0.70

 viewDidLoad

-0.68

 contextLoads

-0.63

 numberOfRows

-0.63

脚注の使い方

-0.63

principalTable

-0.62

Бахар

-0.61

]")]

-0.60

 AssemblyCulture

-0.60

POSITIVE LOGITS

 final

0.72

 report

0.68

 residual

0.60

 recap

0.60

總結

0.58

 Afterward

0.57

Afterwards

0.57

 elog

0.55

 итого

0.55

 summary

0.55

Activations Density 0.855%

phrases discussing cause and effect relationships or outcomes

No Comments

No Known Activations