INDEX

Explanations

specific instances and conditions relevant to case studies or examples

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

kosť

-0.48

 scomp

-0.46

 kautta

-0.46

 barriers

-0.46

though

-0.45

 ceci

-0.45

 вол

-0.45

 autrefois

-0.45

WAVE

-0.45

GOL

-0.44

POSITIVE LOGITS

########.

0.75

utilisons

0.71

TintMode

0.71

новниш

0.69

CppCodeGen

0.64

contentLoaded

0.64

Begriffsklä

0.64

EndContext

0.64

ínű

0.63

AndEndTag

0.63

Activations Density 0.288%

specific instances and conditions relevant to case studies or examples

No Comments

No Known Activations