INDEX

Explanations

references to personal ownership or experiences, often indicated by the word "my" or possessive phrases

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

Follows "My" and signals a personal expression (opinion, feeling, etc.)

np_acts-logits-general · gemini-2.0-flash

My followed by personal pronouns or nouns

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

jsonwebtoken

-0.69

="/">

-0.54

 AssemblyTitle

-0.53

ﷺ

-0.53

ImageContext

-0.51

 בארץ

-0.50

 aguda

-0.49

ännande

-0.48

 springfox

-0.48

}$

-0.48

POSITIVE LOGITS

 apologies

0.69

0.67

 guess

0.66

 dear

0.64

fjspx

0.62

guess

0.55

 favorite

0.55

laps

0.54

 Goodness

0.54

 goodness

0.53

Activations Density 0.126%

references to personal ownership or experiences, often indicated by the word "my" or possessive phrases

Follows "My" and signals a personal expression (opinion, feeling, etc.)

My followed by personal pronouns or nouns

No Comments

No Known Activations