INDEX

Explanations

references to recent events or notable mentions

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 élections

-0.63

الحياه

-0.63

 grève

-0.60

ArgsConstructor

-0.60

Malley

-0.57

hlm

-0.56

uters

-0.55

 चीज़ों

-0.54

 universelle

-0.54

NetworkInfo

-0.54

POSITIVE LOGITS

 importantly

0.56

ViewFeatures

0.53

 trav

0.52

brood

0.48

sig

0.44

trav

0.43

 المعرف

0.42

baldi

0.42

ThroughAttribute

0.41

Kaieteur

0.40

Activations Density 0.264%

references to recent events or notable mentions

No Comments

No Known Activations