INDEX

Explanations

terms related to change or modification

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Mérimée

-0.58

ximity

-0.52

 mattino

-0.51

 McCulloch

-0.50

 připo

-0.47

'));

-0.47

 forbin

-0.46

postDelayed

-0.46

Tē

-0.46

intera

-0.45

POSITIVE LOGITS

 change

2.12

 Change

1.98

 changes

1.98

 changing

1.95

 changed

1.89

Change

1.89

 Changing

1.87

 CHANGE

1.86

 Changes

1.85

changes

1.85

Activations Density 0.394%

terms related to change or modification

No Comments

No Known Activations