INDEX

Explanations

statements indicating the progression or construction of logical arguments

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.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

GEBURTSDATUM

-1.20

تقاوى

-1.15

хьтан

-0.86

IUrlHelper

-0.84

Спољашње

-0.80

InstrumentedTest

-0.79

 beginnetje

-0.78

StoryboardSegue

-0.78

SharedCtor

-0.76

 typelib

-0.75

POSITIVE LOGITS

CTYPE

0.43

Lel

0.43

 realidad

0.42

ποτε

0.41

HOUT

0.41

навли

0.41

is

0.41

MERCIAL

0.40

ouv

0.39

ազմ

0.39

Activations Density 0.575%

statements indicating the progression or construction of logical arguments

No Comments

No Known Activations