INDEX

Explanations

words that imply functionality or capability

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

RegressionTest

-0.70

ing

-0.70

-0.68

 useEffect

-0.67

 AspNetCore

-0.63

Pyx

-0.63

setopt

-0.60

+#+

-0.59

-0.58

POSITIVE LOGITS

izable

1.53

vable

1.52

able

1.45

chable

1.36

ABLE

1.36

atable

1.34

gable

1.33

urable

1.33

asable

1.30

pable

1.26

Activations Density 0.256%

words that imply functionality or capability

No Comments

No Known Activations