INDEX

Explanations

contextual cues related to programming functions and their parameters

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

Code snippets with error messages

np_acts-logits-general · gemini-2.0-flash

2D code and mathematical concepts

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Aven

-0.73

 venti

-0.73

 Schwe

-0.69

 Senti

-0.66

ulti

-0.65

arent

-0.64

פרי

-0.64

","");

-0.62

Aven

-0.62

ZZZZ

-0.61

POSITIVE LOGITS

Przypisy

1.27

Viitteet

0.88

MigrationBuilder

0.87

 Silurian

0.85

 AssemblyCulture

0.82

 sherds

0.80

SizeF

0.79

wiście

0.78

ⓘ

0.78

 alimentaires

0.78

Activations Density 0.650%

contextual cues related to programming functions and their parameters

Code snippets with error messages

2D code and mathematical concepts

No Comments

No Known Activations