INDEX

Explanations

references to prior information or previously established concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_6/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.6.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

addPreferredGap

-0.71

 مرئيه

-0.70

TypedDataSet

-0.68

SequentialGroup

-0.64

Хьажоргаш

-0.61

oush

-0.60

NewUrlParser

-0.59

IsContent

-0.59

SharedCtor

-0.59

%)$

-0.57

POSITIVE LOGITS

 above

1.53

above

1.29

Above

1.12

 Above

1.09

 ABOVE

1.04

 foregoing

1.03

 acima

1.03

 выше

0.99

 ovan

0.92

 diatas

0.91

Activations Density 0.614%

references to prior information or previously established concepts

No Comments

No Known Activations