INDEX

Explanations

references to the concept of "that" in various contexts

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

tagHelperRunner

-0.63

Portale

-0.53

 TextAppearance

-0.51

uffe

-0.50

regate

-0.49

 ezért

-0.48

 GenerationType

-0.48

ágos

-0.47

ebb

-0.47

ussis

-0.45

POSITIVE LOGITS

 which

0.90

 whose

0.85

which

0.84

脚注の使い方

0.80

 jonka

0.77

تقاوى

0.75

Geplaatst

0.75

 cuyos

0.74

whose

0.74

 Whose

0.73

Activations Density 0.476%

references to the concept of "that" in various contexts

No Comments

No Known Activations