INDEX

Explanations

sections of text with no notable content or activations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

Coordenadas

-0.52

 what

-0.50

cre

-0.49

par

-0.47

 goal

-0.47

pat

-0.46

⁠

-0.46

“

-0.46

 ми

-0.46

POSITIVE LOGITS

 '\\;'

0.86

oneofs

0.81

DockStyle

0.79

UnusedPrivate

0.78

 للاسماء

0.78

TagMode

0.77

 AssemblyTitle

0.77

 للمعارف

0.76

oredCriteria

0.75

UrlResolution

0.74

Activations Density 0.086%

sections of text with no notable content or activations

No Comments

No Known Activations