INDEX

Explanations

code structures and types related to arrays and list manipulation in programming

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

start_of_turn user

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-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

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

 referenties

-0.49

TintMode

-0.47

CrossRef

-0.46

 extract

-0.43

acyj

-0.43

 Knud

-0.43

tvguidetime

-0.41

 insist

-0.40

ⓘ

-0.39

PWR

-0.39

POSITIVE LOGITS

MigrationBuilder

0.65

 سكانية

0.49

 gabbana

0.47

 ब्रेकडाउन

0.45

 GenerationType

0.44

RenderAtEndOf

0.43

 AssemblyCompany

0.42

 censiti

0.42

 bershka

0.41

RectangleBorder

0.40

Activations Density 0.019%

code structures and types related to arrays and list manipulation in programming

start_of_turn user

No Comments

No Known Activations