INDEX

Explanations

references to the term "dig" and its variations in different contexts

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

dig followed by nam, gers, enic

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

 itemId

-0.59

wana

-0.59

eni

-0.51

DREN

-0.50

ana

-0.49

 Lombardo

-0.49

lana

-0.49

rika

-0.48

mana

-0.47

<bos>

-0.47

POSITIVE LOGITS

dig

2.38

Dig

2.36

Dig

2.28

DIG

1.98

dig

1.84

DIG

1.78

 digs

1.67

 digging

1.55

 digger

1.54

dug

1.38

Activations Density 0.005%

references to the term "dig" and its variations in different contexts

dig followed by nam, gers, enic

No Comments

No Known Activations