INDEX

Explanations

expressions and conditions related to CUDA results and control flow statements

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

 ***!

-0.60

 invokingState

-0.55

mainAxisSize

-0.52

por

-0.51

enderror

-0.51

niająca

-0.51

Por

-0.50

Nor

-0.49

Rä

-0.49

RuleContext

-0.49

POSITIVE LOGITS

peq

0.63

 disambiguazione

0.63

évaluateur

0.62

 voorbij

0.59

 šķ

0.59

 hendes

0.58

 CascadeType

0.54

 économies

0.53

 RIPRODUZIONE

0.52

 zwier

0.52

Activations Density 0.850%

expressions and conditions related to CUDA results and control flow statements

No Comments

No Known Activations