INDEX

Explanations

instances of the word "letter" and its variations

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

setVerticalGroup

-0.60

 Lovato

-0.58

GetEnumerator

-0.57

 absoluto

-0.57

 متحده

-0.57

 كمان

-0.56

cassert

-0.56

delaire

-0.55

NORE

-0.55

ertor

-0.54

POSITIVE LOGITS

 letters

0.86

Letters

0.78

 Letters

0.76

 CreateTagHelper

0.71

 LETTERS

0.70

GOTREF

0.66

letters

0.66

 LETTER

0.64

bootstrapcdn

0.63

 alphabet

0.59

Activations Density 0.134%

instances of the word "letter" and its variations

No Comments

No Known Activations