INDEX

Explanations

structured formatting or syntactical markers in code

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

 мәкал

-0.76

postIndex

-0.73

 tslint

-0.70

+#+#

-0.69

 ***!

-0.69

ſelves

-0.68

findpost

-0.66

Portale

-0.65

SharedCtor

-0.64

 NSCoder

-0.64

POSITIVE LOGITS

↵

0.60

<unused63>

0.52

 Utilities

0.51

setImageBitmap

0.51

utils

0.49

ptonshire

0.48

putBoolean

0.48

Slf

0.47

<unused62>

0.47

<unused61>

0.47

Activations Density 0.167%

structured formatting or syntactical markers in code

No Comments

No Known Activations