INDEX

Explanations

terms related to scientific observations or measurements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 CreateTagHelper

-1.07

 SwiftUI

-0.91

nosaurus

-0.85

iecie

-0.81

 podjela

-0.81

 nakalista

-0.80

 lenker

-0.78

 Alcott

-0.77

 Patsy

-0.75

POSITIVE LOGITS

ly

2.40

LY

1.38

theless

1.19

mente

1.14

fully

1.03

tably

0.98

lyn

0.94

 fufficient

0.94

maßen

0.91

lyk

0.91

Activations Density 0.386%

terms related to scientific observations or measurements

No Comments

No Known Activations