INDEX

Explanations

modifiers that indicate degrees of intensity or quantity

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

 незавершена

-0.66

 relatively

-0.64

 sufficiently

-0.63

 enormously

-0.61

 tremendously

-0.60

relatively

-0.60

 utterly

-0.58

 greatly

-0.57

 pauv

-0.57

 betyd

-0.56

POSITIVE LOGITS

ValueStyle

0.83

bit

0.77

tagext

0.74

SourceChecksum

0.72

づ

0.67

ずつ

0.67

씩

0.66

adə

0.64

 unknownFields

0.63

PROLOG

0.61

Activations Density 0.121%

modifiers that indicate degrees of intensity or quantity

No Comments

No Known Activations