INDEX

Explanations

instances of numeric data, particularly related to scoring or timing events

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

homonymie

-0.62

Rhestr

-0.56

gama

-0.53

delwed

-0.51

antd

-0.51

EDEFAULT

-0.51

 odeur

-0.50

>[]

-0.49

لينكات

-0.47

 FishBase

-0.47

POSITIVE LOGITS

 minute

0.79

RectangleBorder

0.73

 minutes

0.72

mins

0.69

min

0.68

minute

0.68

min

0.67

 MINUTE

0.66

 mins

0.65

 menit

0.65

Activations Density 0.509%

instances of numeric data, particularly related to scoring or timing events

No Comments

No Known Activations