INDEX

Explanations

elements related to data processing or file manipulation commands

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

Code, math, or file paths

np_acts-logits-general · gemini-2.0-flash

INT or code identifiers

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

"}";

-0.50

เป๋า

-0.48

WireFormat

-0.47

-0.46

asının

-0.45

"}")

-0.41

Ins

-0.41

bal

-0.41

lo

-0.41

crombie

-0.41

POSITIVE LOGITS

Jegyzetek

0.78

 pouvoit

0.69

 étoit

0.68

 onOptions

0.66

 feroit

0.65

 CreateTagHelper

0.64

TagHelper

0.64

OGND

0.63

 auroit

0.61

 ClassNotFound

0.61

Activations Density 1.038%

elements related to data processing or file manipulation commands

Code, math, or file paths

INT or code identifiers

No Comments

No Known Activations