INDEX

Explanations

terms related to training methods and their effectiveness

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

Tokens often preceding code snippets or technical terms

np_acts-logits-general · gemini-2.0-flash

technical terms 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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

AddTagHelper

-1.29

 nahilalakip

-1.25

IsMutable

-1.15

adaptiveStyles

-1.10

IsContent

-1.09

SourceChecksum

-1.08

 snippetHide

-1.06

CodedInputStream

-1.03

FunctionFlags

-1.02

RTSC

-1.01

POSITIVE LOGITS

że

0.52

anueva

0.46

ὖ

0.46

事儿

0.45

chuckles

0.44

 referenties

0.43

 appunto

0.42

️

0.42

the

0.41

icamente

0.40

Activations Density 1.282%

terms related to training methods and their effectiveness

Tokens often preceding code snippets or technical terms

technical terms and specific words

No Comments

No Known Activations