INDEX

Explanations

content discussing statistical analysis and data interpretation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

eds

-0.45

 Wide

-0.42

Dit

-0.42

сть

-0.41

 selve

-0.41

Their

-0.40

 THEIR

-0.40

WebVitals

-0.40

ocities

-0.38

따

-0.38

POSITIVE LOGITS

 himself

1.15

 للمعارف

1.10

himself

0.98

 تانيه

0.88

 发表于

0.82

ніципалі

0.81

 himſelf

0.81

RTEX

0.78

Diwedd

0.76

InjectAttribute

0.75

Activations Density 0.533%

content discussing statistical analysis and data interpretation

No Comments

No Known Activations