INDEX

Explanations

phrases that express evaluations or opinions about situations or experiences

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

 müm

-0.50

Spire

-0.47

EXPECTED

-0.45

Hướng

-0.45

 expected

-0.43

minaire

-0.41

 esperado

-0.41

 gezogen

-0.40

 Opener

-0.40

 mourut

-0.40

POSITIVE LOGITS

IntoConstraints

0.87

memoized

0.76



0.73

ConverterFactory

0.70

rlpool

0.67

%)$

0.65

 nahilalakip

0.65

 convertView

0.63

DIPSETTING

0.63

 stable

0.63

Activations Density 0.233%

phrases that express evaluations or opinions about situations or experiences

No Comments

No Known Activations