INDEX

Explanations

dialogues that include questions and responses about clarification or understanding

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

gpl

-0.61

 compter

-0.58

 pungkasnya

-0.53

 kalah

-0.52

 Juga

-0.48

yszcz

-0.47

पित

-0.47

äumt

-0.46

væ

-0.46

imanapun

-0.46

POSITIVE LOGITS

 TextAppearance

0.73

 enquired

0.70

ContentAsync

0.69

ItemBackground

0.66

 queried

0.65

出版年

0.64

 asked

0.64

 enquiry

0.62

تقاوى

0.61

 inquiry

0.61

Activations Density 0.170%

dialogues that include questions and responses about clarification or understanding

No Comments

No Known Activations