INDEX

Explanations

numeric quantifications and comparisons

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

<eos>

-0.56

setOn

-0.50

lec

-0.50

-0.49

 Full

-0.47

Full

-0.46

nyata

-0.46

 full

-0.46

Top

-0.45

Top

-0.45

POSITIVE LOGITS

IsContent

0.95

abestanden

0.90

 '\\;'

0.90

 snippetHide

0.89

 HasFactory

0.89

antaine

0.86

Демографія

0.86

 <>",

0.84

__*/

0.84

########.

0.84

Activations Density 0.279%

numeric quantifications and comparisons

No Comments

No Known Activations