INDEX

Explanations

filler words and phrases that undermine communication

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Dilution

-0.48

 arit

-0.44

Magical

-0.43

Symbolic

-0.42

 Antimicrobial

-0.42

 Discovering

-0.41

 Dirty

-0.41

 Rotating

-0.41

External

-0.40

 Racial

-0.40

POSITIVE LOGITS

 كومونز

0.99

 للمعارف

0.93

 snippetHide

0.86

expandindo

0.83

ChildScrollView

0.83

aarrggbb

0.82

AlterField

0.79

 initComponents

0.78

IsPostBack

0.78

argout

0.78

Activations Density 0.203%

filler words and phrases that undermine communication

No Comments

No Known Activations