INDEX

Explanations

definitions and structures related to programming constructs and functions

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

Iterating through items or lines

np_acts-logits-general · gemini-2.0-flash

separate entities or items

np_acts-logits-general · gemini-2.5-flash-lite

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

 resourceCulture

-0.73

évaluateur

-0.52

↵↵

-0.50

tvguidetime

-0.48

 pulang

-0.45

 ligiloj

-0.45

)++;

-0.44

 disambiguazione

-0.43

<eos>

-0.42

 springfox

-0.41

POSITIVE LOGITS

 each

0.81

each

0.78

 apiece

0.78

EACH

0.68

tagext

0.67

 незавершена

0.65

 separately

0.64

 EACH

0.64

 actionTypes

0.63

而言

0.63

Activations Density 0.077%

definitions and structures related to programming constructs and functions

Iterating through items or lines

separate entities or items

No Comments

No Known Activations