INDEX

Explanations

terms related to evaluation and comparison of items or entities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

·

-0.57

&#

-0.54

<h6>

-0.51

\\

-0.47

•

-0.46

-0.44

burgo

-0.44

•

-0.41

&#

-0.40

■

-0.39

POSITIVE LOGITS

 فريبيس

1.03

 esternos

0.92

 онъ

0.88

 متعلقه

0.87

IntoConstraints

0.86

 oregon

0.85

aarrggbb

0.83

 betweenstory

0.82

 myſelf

0.82

 caller

0.80

Activations Density 0.087%

terms related to evaluation and comparison of items or entities

No Comments

No Known Activations