INDEX

Explanations

various punctuation marks and separators commonly used in coding and data formatting

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

-0.69

le

-0.57

bu

-0.57

 deep

-0.56

<u>

-0.55

leg

-0.53

zu

-0.52

be

-0.52

↵↵

-0.51

du

-0.50

POSITIVE LOGITS

TintMode

0.99

 GeoNames

0.99

StructEnd

0.98

 Савезне

0.98

MessageTagHelper

0.97

 '\\;'

0.96

SBATCH

0.95

parsedMessage

0.94

CloseOperation

0.91

 myſelf

0.90

Activations Density 0.459%

various punctuation marks and separators commonly used in coding and data formatting

No Comments

No Known Activations