INDEX

Explanations

expressions of preference and comparative judgments

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

 Audiodateien

-0.74

xDB

-0.70

liters

-0.67

 plot

-0.67

Al

-0.67

Hil

-0.65

Gil

-0.64

 James

-0.64

Dum

-0.61

mybatisplus

-0.60

POSITIVE LOGITS

 prefer

1.38

 Prefer

1.38

 prefers

1.35

prefer

1.34

 préfé

1.33

 preferred

1.32

 Preferred

1.30

preferred

1.27

 preference

1.26

 Preference

1.23

Activations Density 0.077%

expressions of preference and comparative judgments

No Comments

No Known Activations