INDEX

Explanations

the prefixes "co-" or "the"

oai_token-act-pair · gemini-2.0-flash

co-occurrence patterns and related terms

np_token-act-pair-logits · gpt-4o-mini

co

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

styleable

-0.53

 referenties

-0.51

WaitGroup

-0.46

PerformLayout

-0.45

mobileqq

-0.43

 estimés

-0.42

timewa

-0.41

thme

-0.41

 handen

-0.40

tagext

-0.40

POSITIVE LOGITS

ⓧ

0.67

 CreateTagHelper

0.64

Personensuche

0.58

 препратки

0.55

 Stretcher

0.54

цездатний

0.54

 Drapeau

0.52

 BufferedReader

0.52

Meik

0.52

Activations Density 0.138%

the prefixes "co-" or "the"

co-occurrence patterns and related terms

co

No Comments

No Known Activations