INDEX

Explanations

specific formatting or styling indicators in text, particularly related to mathematical expressions and notation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91

Prompts (Dashboard)

24,576 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

+#+#

-0.92

tagHelperRunner

-0.90

 AssemblyCompany

-0.90

sidemargin

-0.78

bootstrapcdn

-0.77

estacks

-0.75

WriteTagHelper

-0.72

ftagPool

-0.72

WithIOException

-0.69

 ExecuteAsync

-0.68

POSITIVE LOGITS

“

0.32

тном

0.32

0.31

 Fischer

0.31

']}

0.30

 Nieder

0.30

vol

0.29

 Nielsen

0.29

isNotBlank

0.28

Pre

0.28

Activations Density 1.088%

specific formatting or styling indicators in text, particularly related to mathematical expressions and notation

No Comments

No Known Activations