INDEX

Explanations

quantitative measurements and distances

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

 विश्वसनीयता

-0.52

حوالہ

-0.49

 muito

-0.48

ScopeManager

-0.47

iredo

-0.46

citep

-0.45

 Nearly

-0.45

stalt

-0.45

Word

-0.44

reathe

-0.44

POSITIVE LOGITS

 away

1.40

 ahead

1.06

away

0.96

 apart

0.93

shy

0.93

 above

0.93

 behind

0.90

 AWAY

0.89

 below

0.86

Away

0.83

Activations Density 0.214%

quantitative measurements and distances

No Comments

No Known Activations