INDEX

Explanations

references to bibliographic or informational sources

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

IntoConstraints

-0.68

 AssemblyTitle

-0.66

 CURIAM

-0.64

prepareStatement

-0.61

@"/

-0.58

 createState

-0.56

AndroidJUnit

-0.56

createStatement

-0.55

parsedMessage

-0.55

 "..\..\

-0.55

POSITIVE LOGITS

 dictionary

1.18

 Dictionary

1.15

Encyclopedia

1.04

 encyclopedia

1.03

Dictionary

1.01

 Encyclopedia

1.00

lossary

0.98

 directory

0.96

dictionary

0.94

 Dictionnaire

0.90

Activations Density 0.282%

references to bibliographic or informational sources

No Comments

No Known Activations