INDEX

Explanations

technical terms and names related to specific organisms or biochemical compounds

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

intero

-0.41

 nevera

-0.41

-0.40

phère

-0.40

TagHelper

-0.39

 Nerven

-0.39

 ProgressDialog

-0.38

↵↵

-0.38

ArgsConstructor

-0.37

 ото

-0.37

POSITIVE LOGITS

NUMX

1.09

MessageState

0.94

 Houſe

0.91

 myſelf

0.91

 xmax

0.89

 Jefus

0.89

 XCTest

0.86

XG

0.86

 Monfieur

0.85

 maxX

0.85

Activations Density 0.243%

technical terms and names related to specific organisms or biochemical compounds

No Comments

No Known Activations