INDEX

Explanations

sections of text related to numerical data or statistical results, particularly in academic or scientific contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

NameInMap

-0.70

+#+#

-0.66

 nahilalakip

-0.65

aarrggbb

-0.61

ⓧ

-0.61

TypedDataSet

-0.60

 resourceCulture

-0.60

AndroidJUnit

-0.59

 continuant

-0.59

dostęp

-0.59

POSITIVE LOGITS

 passim

0.53

']):

0.51

 auftreten

0.47

✨:

0.47

 worshipped

0.45

 untitled

0.45

iastes

0.44

acaktır

0.44

$.}

0.43

efficacité

0.43

Activations Density 0.143%

sections of text related to numerical data or statistical results, particularly in academic or scientific contexts

No Comments

No Known Activations