INDEX

Explanations

sections of text that contain no activations, indicating it does not detect any specific features or topics

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

Code snippets or file paths

np_acts-logits-general · gemini-2.0-flash

numerical literals

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

CppMethod

-0.61

万美元

-0.54

CppCodeGen

-0.53

runApp

-0.52

nehå

-0.48

OrBuilder

-0.48

khart

-0.48

ccin

-0.47

碼

-0.47

 chère

-0.46

POSITIVE LOGITS

ftagPool

0.76

TagMode

0.73

isContained

0.58

GEBURTSDATUM

0.57

MigrationBuilder

0.56

uertos

0.55

COUVER

0.54

 Kombat

0.54

revert

0.53

 typelib

0.52

Activations Density 0.007%

sections of text that contain no activations, indicating it does not detect any specific features or topics

Code snippets or file paths

numerical literals

No Comments

No Known Activations