INDEX

Explanations

terms related to broad or generalized concepts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.8.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

()?;

-0.95

AccessFile

-0.95

TemporalType

-0.92

ypsies

-0.90

évaluateur

-0.90

nocache

-0.89

ंदीखरीदारी

-0.88

uari

-0.87

 DBNull

-0.87

ари

-0.84

POSITIVE LOGITS

 Broad

0.98

Broad

0.97

 Brod

0.94

broad

0.93

 BROAD

0.81

 broad

0.80

([^

0.79

bro

0.70

 Crow

0.69

Bro

0.68

Activations Density 0.109%

terms related to broad or generalized concepts

No Comments

No Known Activations