INDEX

Explanations

words related to computer software

oai_token-act-pair · gemini-2.0-flash

terms related to analytics and documentation sections

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

webpage sections

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

ſelves

-0.87

 uſed

-0.81

 Jefus

-0.80

ſelf

-0.80

 ſeveral

-0.79

 تانيه

-0.77

__(/*!

-0.76

 itſelf

-0.75

 myſelf

-0.75

 juſ

-0.74

POSITIVE LOGITS

 area

0.85

 section

0.77

 page

0.71

area

0.64

section

0.60

 sheet

0.57

sec

0.57

 platform

0.57

 list

0.56

 List

0.55

Activations Density 2.051%

words related to computer software

terms related to analytics and documentation sections

webpage sections

No Comments

No Known Activations