INDEX

Explanations

specific terms and phrases related to coding, programming, or technical details

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

Code or configuration snippets

np_acts-logits-general · gemini-2.0-flash

Q phrases, code delimiters, and specific words

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 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

MigrationBuilder

-1.38

StoryboardSegue

-1.22

 Paglinawan

-1.18

 surla

-1.13

 nahilalakip

-1.10

SourceChecksum

-1.08

argout

-1.08

 MainAxisSize

-1.06

 aDecoder

-1.06

ratulations

-1.05

POSITIVE LOGITS

ania

0.45

ur

0.45

io

0.44

’

0.44

0.43

wer

0.42

↵↵

0.42

Activations Density 0.524%

specific terms and phrases related to coding, programming, or technical details

Code or configuration snippets

Q phrases, code delimiters, and specific words

No Comments

No Known Activations