INDEX

Explanations

elements related to programming constructs and operations

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

Code or special characters

np_acts-logits-general · gemini-2.0-flash

code snippets and programming constructs

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91

Prompts (Dashboard)

24,576 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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

stdc

-0.31

 сам

-0.27

 ancillary

-0.25

borderTop

-0.25

context

-0.25

background

-0.25

 directa

-0.25

na

-0.24

 Ausbildung

-0.24

licité

-0.24

POSITIVE LOGITS

expandindo

0.93

rungsseite

0.91

 EconPapers

0.90

 disambiguazione

0.86

 дописавши

0.79

 ujednoznacz

0.78

 noDo

0.77

verwijspagina

0.76

+#+#

0.74

 InputDecoration

0.73

Activations Density 0.297%

elements related to programming constructs and operations

Code or special characters

code snippets and programming constructs

No Comments

No Known Activations