INDEX

Explanations

phrases indicating affirmation or emphasis

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

tvguidetime

-0.89



-0.65

WriteTagHelper

-0.65

WebElementEntity

-0.59

zarchiwizowane

-0.58

archiviato

-0.57

principalColumn

-0.56

 HasFactory

-0.56

RegressionTest

-0.54

onsored

-0.54

POSITIVE LOGITS

0.84

’

0.81

´

0.73

0.68

رشف

0.67

 sounds

0.64

 means

0.60

is

0.57

 sums

0.55

′

0.53

Activations Density 0.127%

phrases indicating affirmation or emphasis

No Comments

No Known Activations