INDEX

Explanations

linguistic elements related to reasoning and questioning

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

httphttps

-0.56

omores

-0.51

uitable

-0.48

amethasone

-0.47

çais

-0.47

を受けた

-0.47

 sumpay

-0.46

himovic

-0.46

र्भ

-0.46

請繼續往下閱讀

-0.44

POSITIVE LOGITS

 things

2.94

 everything

2.52

Things

2.49

 Things

2.40

things

2.39

everything

2.33

 THINGS

2.27

Everything

2.24

 Everything

2.18

 EVERYTHING

1.82

Activations Density 0.471%

linguistic elements related to reasoning and questioning

No Comments

No Known Activations