INDEX

Explanations

relationships between concepts and their definitions or implications

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-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

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

 '\\;'

-0.71

MemoryWarning

-0.70

}{@

-0.62

 AssemblyCulture

-0.61

UrlResolution

-0.60

 IconData

-0.59

enderror

-0.57

SharedDtor

-0.55

rawDesc

-0.55

ähteet

-0.55

POSITIVE LOGITS

 offend

0.33

Sucesor

0.30

scan

0.29

 direct

0.28

 spin

0.27

amını

0.26

 acı

0.26

fadeOut

0.24

 öld

0.24

zungs

0.24

Activations Density 0.102%

relationships between concepts and their definitions or implications

No Comments

No Known Activations