INDEX

Explanations

conditional phrases indicating potential outcomes or possibilities

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

 viewType

-0.76

 CURIAM

-0.74

 nawr

-0.69

InvalidProtocol

-0.66

Tembelea

-0.64

 FontWeight

-0.63

помним

-0.63

soort

-0.62

ReusableCell

-0.61

CWE

-0.61

POSITIVE LOGITS

 potentially

1.28

 conceivably

1.27

 easily

1.11

 possibly

1.09

potentially

1.04

 theoretically

1.00

 well

0.93

 potential

0.90

easily

0.89

 possible

0.88

Activations Density 0.117%

conditional phrases indicating potential outcomes or possibilities

No Comments

No Known Activations