INDEX

Explanations

code imports in programming contexts

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

Lines starting with "import" or "require"

np_acts-logits-general · gemini-2.0-flash

import from

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.9.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

 pleaſure

-0.58

 itſelf

-0.57

 ſind

-0.56

 ſta

-0.54

ſelf

-0.53

 faſt

-0.52

 ſche

-0.52

AISSEE

-0.51

 Anſ

-0.50

neſs

-0.49

POSITIVE LOGITS

 from

0.73

 AssemblyCulture

0.53

from

0.48

the

0.46

 among

0.45

__(/*!

0.45

 lingkungan

0.44

 gelombang

0.44

 FROM

0.43

จาก

0.43

Activations Density 0.055%

code imports in programming contexts

Lines starting with "import" or "require"

import from

No Comments

No Known Activations