INDEX

Explanations

words and phrases indicating effectiveness, significance, and quality in various contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 betweenstory

-1.33

LookAnd

-1.08

GEBURTSDATUM

-1.04

AndEndTag

-1.01

RegressionTest

-0.99

sidemargin

-0.96

enderror

-0.96

 AssemblyCompany

-0.93

 الحره

-0.93

 للمعارف

-0.93

POSITIVE LOGITS

 enough

1.08

to

0.82

for

0.76

in

0.66

and

0.63

enough

0.60

ly

0.59

 about

0.57

as

0.57

 from

0.56

Activations Density 0.771%

words and phrases indicating effectiveness, significance, and quality in various contexts

No Comments

No Known Activations