INDEX

Explanations

terms related to processes of standardization or categorization

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

fcntl

-0.82

 colleg

-0.80

 noten

-0.76

TRO

-0.71

튼

-0.65

 COUR

-0.63

tpl

-0.63

 Pekan

-0.62

((

-0.62

tro

-0.61

POSITIVE LOGITS

ization

1.09

ilized

1.03

ifiers

1.03

ized

1.03

olesale

1.03

AutoresizingMask

0.98

lizes

0.94

alisation

0.93

 himſelf

0.91

 myſelf

0.91

Activations Density 0.308%

terms related to processes of standardization or categorization

No Comments

No Known Activations