INDEX

Explanations

definitions and declarations related to classes in programming

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

in

-0.64

on

-0.60

al

-0.57

to

-0.56

and

-0.55

that

-0.55

this

-0.55

the

-0.53

st

-0.53

POSITIVE LOGITS

帖最后由

1.24

GEBURTSDATUM

1.09

 tartalomajánló

1.08

#+#

1.05

ⓧ

0.99

rungsseite

0.92

expandindo

0.88

SourceChecksum

0.86

adaptiveStyles

0.86

setVerticalGroup

0.86

Activations Density 0.062%

definitions and declarations related to classes in programming

No Comments

No Known Activations