INDEX

Explanations

phrases indicating personal experiences or reflections

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

preposition followed by "the"

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

存于互联网档案馆

-0.66

ագրություններ

-0.65

RSpec

-0.64

⟬

-0.63

EndInit

-0.60

 XMLHttpRequest

-0.60

Дереккөздер

-0.59

Rptr

-0.57

TagMode

-0.57

 Spas

-0.57

POSITIVE LOGITS

Vezi

0.42

 intér

0.41

the

0.40

Decrement

0.39

 capacitación

0.35

 inspección

0.35

 Aufg

0.35

 prácti

0.34

să

0.34

 нержа

0.34

Activations Density 0.039%

phrases indicating personal experiences or reflections

preposition followed by "the"

No Comments

No Known Activations