INDEX

Explanations

textual formatting or structured data elements

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

<eos>

-0.58

Bau

-0.53

...

-0.50

 competitive

-0.49

jak

-0.49

 compren

-0.48

sei

-0.48

 Wild

-0.48

 <<<<<<<<<<<<<<

-0.48

POSITIVE LOGITS

 Roskov

0.91

Efq

0.90

contentLoaded

0.80

 فريبيس

0.77

 iſt

0.76

 Majefty

0.75

 Shakspeare

0.74

 houſe

0.73

 ſmall

0.73

 greateſt

0.73

Activations Density 0.142%

textual formatting or structured data elements

No Comments

No Known Activations