INDEX

Explanations

references to research methodologies and healthcare practices

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

if

-0.71

 Anyway

-0.68

 kalau

-0.65

 Правда

-0.65

 hvis

-0.64

 Nobody

-0.63

Anyway

-0.63

 nếu

-0.63

apparently

-0.61

Apparently

-0.61

POSITIVE LOGITS

 Through

1.13

Through

1.11

Key

1.03

Key

1.00

 Specifically

0.96

key

0.95

Specifically

0.92

 Particular

0.85

 Specific

0.84

Specific

0.81

Activations Density 0.631%

references to research methodologies and healthcare practices

No Comments

No Known Activations