INDEX

Explanations

quantitative rankings and classifications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.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

 LinearLayout

-0.62

 &___

-0.60

为止

-0.59

spania

-0.58

 GetEnumerator

-0.58

 QtWidgets

-0.56

 تانيه

-0.56

 Reſ

-0.56

 AppBar

-0.56

 iNdEx

-0.55

POSITIVE LOGITS

يكب

0.61

 seventh

0.57

seventh

0.55

esimo

0.54

 ninth

0.54

涯

0.52

ninth

0.51

 eighth

0.50

λίου

0.50

own

0.50

Activations Density 0.386%

quantitative rankings and classifications

No Comments

No Known Activations