INDEX

Explanations

references to authors and their contributions

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

Tokens appearing before dates or names

np_acts-logits-general · gemini-2.0-flash

by news reporters or authors

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.16.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

CloseOperation

-0.81

 CreateTagHelper

-0.77

 صوتيه

-0.75

ContentAsync

-0.74

DockStyle

-0.71

 InputDecoration

-0.69

 OBITUARY

-0.69

ViewImports

-0.68

 متعلقه

-0.68

tvguidetime

-0.65

POSITIVE LOGITS

addGap

0.55

↵↵

0.47

乎

0.43

########.

0.41

glises

0.41

ियाँ

0.40

 personally

0.40

Cyfarwyddwr

0.40

ставля

0.39

addPreferredGap

0.39

Activations Density 0.235%

references to authors and their contributions

Tokens appearing before dates or names

by news reporters or authors

No Comments

No Known Activations