INDEX

Explanations

occurrences of the word "self" in various contexts

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

class method self argument

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.9.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

Atm

-0.42

HICLE

-0.41

)•

-0.41

Ӕ

-0.40

libft

-0.39

Irv

-0.38

 Tumor

-0.38

 chim

-0.38

Tumor

-0.37

ardige

-0.37

POSITIVE LOGITS

self

1.07

 self

0.94

 Self

0.74

Self

0.74

 SELF

0.65

SELF

0.64

自我

0.61

AnchorStyles

0.61

 nahilalakip

0.60

rungsseite

0.60

Activations Density 0.003%

occurrences of the word "self" in various contexts

class method self argument

No Comments

No Known Activations