INDEX

Explanations

references to personal achievements and historical impacts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

 intptr

-0.55

rawDesc

-0.48

EOUS

-0.47

haped

-0.46

__(/*!

-0.45

 galore

-0.44

 initComponents

-0.44

Réalisation

-0.44

ically

-0.44

rous

-0.44

POSITIVE LOGITS

 zone

0.91

InjectAttribute

0.86

 curve

0.81

 pattern

0.77

 sheet

0.75

 plate

0.74

 line

0.74

TestingModule

0.73

 frame

0.72

 circle

0.70

Activations Density 1.264%

references to personal achievements and historical impacts

No Comments

No Known Activations