INDEX

Explanations

words related to ethical considerations and implications, particularly in the context of animal rights and testing

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

Following specific prefixes

np_acts-logits-general · gemini-2.0-flash

words ending in 'ly' or 'ment' or 'tion'

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

 myſelf

-1.01

 ſta

-0.99

 itſelf

-0.95

 ſhall

-0.90

 ſtill

-0.90

 whoſe

-0.90

 auffi

-0.89

 ſhould

-0.89

Efq

-0.88

 ſtand

-0.87

POSITIVE LOGITS

0.67

ce

0.63

开发者

0.59

et

0.57

ual

0.56

ig

0.56

 capas

0.55

ĺ

0.55

al

0.55

Activations Density 0.432%

words related to ethical considerations and implications, particularly in the context of animal rights and testing

Following specific prefixes

words ending in 'ly' or 'ment' or 'tion'

No Comments

No Known Activations