INDEX

Explanations

numeric values and frequency-related terminology

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

 '*')

-0.67

 gutem

-0.60

 saken

-0.58

 ellers

-0.57

 meste

-0.57

Билгалдахарш

-0.56

Trails

-0.54

\{\\

-0.52

 Audiodateien

-0.52

 persino

-0.52

POSITIVE LOGITS

 number

1.17

 numberOf

1.07

numberOf

0.94

 NUMBER

0.93

 Number

0.92

number

0.91

 fewer

0.85

 "..\..\..\

0.84

NUMBER

0.82

WithMany

0.81

Activations Density 0.251%

numeric values and frequency-related terminology

No Comments

No Known Activations