INDEX

Explanations

expressions of admiration and positive attributes about individuals

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.17.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

oredCriteria

-0.74

EndGlobalSection

-0.72

parsedMessage

-0.68

wußt

-0.66

aptors

-0.66

SequentialGroup

-0.66

]{\

-0.64

+#+#

-0.64

mybatisplus

-0.63

essary

-0.62

POSITIVE LOGITS

 qualities

0.69

 traits

0.69

 Qualities

0.65

his

0.64

who

0.62

traits

0.60

he

0.60

 Traits

0.59

他是

0.55

 Personality

0.54

Activations Density 0.253%

expressions of admiration and positive attributes about individuals

No Comments

No Known Activations