INDEX

Explanations

references to educational courses

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

 Monfieur

-1.09

 للمعارف

-1.04

 uſed

-0.91

 pleaſure

-0.88

 ſta

-0.87

Efq

-0.86

utched

-0.85

 Majefty

-0.85

 myſelf

-0.83

 ainfi

-0.82

POSITIVE LOGITS

 course

2.49

 courses

2.25

 Course

2.21

course

2.16

Course

2.10

 Courses

2.03

 COURSE

2.00

Courses

1.92

COURSE

1.76

courses

1.75

Activations Density 0.042%

references to educational courses

No Comments

No Known Activations