INDEX

Explanations

expressions of belief or opinion

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

حوالہ

-0.53

 pleaſure

-0.52

sū

-0.52

 تمثيل

-0.50

مني

-0.48

 colazione

-0.48

 unterschiedlich

-0.47

 Diſ

-0.47

faj

-0.46

وام

-0.46

POSITIVE LOGITS

 glaube

0.94

 perhaps

0.94

mutlich

0.93

 probably

0.91

 maybe

0.90

Probably

0.87

 probablemente

0.87

perhaps

0.84

 chyba

0.84

 provavelmente

0.83

Activations Density 0.111%

expressions of belief or opinion

No Comments

No Known Activations