INDEX

Explanations

discussions on personal beliefs and values

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

 contigo

-0.85

 بتوان

-0.81

 صوتيه

-0.80

だが

-0.75

 Itself

-0.71

Hochspringen

-0.69

CrossRef

-0.69

だったが

-0.66

 itself

-0.61

 dirinya

-0.61

POSITIVE LOGITS

 yourself

2.21

yourself

1.65

 yourselves

1.55

 Yourself

1.47

 YOURSELF

1.44

 your

1.20

Yourself

1.11

your

0.96

你自己

0.86

 будете

0.83

Activations Density 0.613%

discussions on personal beliefs and values

No Comments

No Known Activations