INDEX

Explanations

instances of the word "this" and its variants

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

"This" followed by a positive descriptor

np_acts-logits-general · gemini-2.0-flash

this introduces positive descriptions

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

ImageContext

-0.73

 ModelExpression

-0.66

principalTable

-0.56

KommentareTeilen

-0.56

JsonPropertyName

-0.55

 personne

-0.53

 entendido

-0.50



-0.48

 ivelany

-0.48

 autocorrelation

-0.47

POSITIVE LOGITS

 particular

0.98

 impressive

0.97

 remarkable

0.91

 gorgeous

0.91

 beautiful

0.87

 amazing

0.87

 lovely

0.86

 delightful

0.86

 incredible

0.85

 powerful

0.85

Activations Density 0.177%

instances of the word "this" and its variants

"This" followed by a positive descriptor

this introduces positive descriptions

No Comments

No Known Activations