INDEX

Explanations

instances of structured format indicators or breaks in the text

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.14.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

варе

-0.48

lung

-0.46

 ress

-0.45

gered

-0.44

axios

-0.44

rangian

-0.43

ностей

-0.42

lée

-0.42

RIC

-0.42

ện

-0.42

POSITIVE LOGITS

findpost

0.85

adaptiveStyles

0.84

 referenties

0.77

 CreateTagHelper

0.76

 AssemblyTitle

0.75

amaño

0.75

Datuak

0.75

 Вікі

0.74

✨:

0.73

Efq

0.73

Activations Density 0.072%

instances of structured format indicators or breaks in the text

No Comments

No Known Activations