INDEX

Explanations

code snippets and technical references, sometimes including brackets, semicolons, tags, and colons

oai_token-act-pair · gemini-2.0-flash

Code snippets and punctuation

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 EconPapers

-0.57

fromnode

-0.56

MigrationBuilder

-0.49

:✨

-0.46

mybatisplus

-0.43

tanleria

-0.43

Rhestr

-0.43

 AspNetCore

-0.42

protoimpl

-0.42

FormTagHelper

-0.40

POSITIVE LOGITS

 gọn

0.63

fleisch

0.59

vgili

0.57

omt

0.55

tispiece

0.55

posição

0.54

 délé

0.54

ihnachts

0.54

 geli

0.53

 bota

0.52

Activations Density 4.188%

code snippets and technical references, sometimes including brackets, semicolons, tags, and colons

Code snippets and punctuation

No Comments

No Known Activations