INDEX

Explanations

occurrences of the word "the."

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 pinulongan

-1.10

addCriterion

-1.04

Personendaten

-0.92

 مرئيه

-0.89

 EconPapers

-0.87

IndentedString

-0.86

awaiter

-0.84

NameInMap

-0.83

 propOrder

-0.81

rungsseite

-0.78

POSITIVE LOGITS

 this

0.61

virano

0.48

getOriginal

0.47

 данного

0.47

 дорогой

0.46

iglio

0.46

obenzene

0.46

 Ganze

0.45

 them

0.44

Activations Density 0.624%

occurrences of the word "the."

No Comments

No Known Activations