INDEX

Explanations

comparative phrases highlighting similarities or analogies

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

 itſelf

-1.04

 raiſ

-1.00

ſelf

-0.94

 pleaſure

-0.93

 Houſe

-0.92

 Anſ

-0.90

 Reſ

-0.88

 Conſ

-0.88

 houſe

-0.87

venidos

-0.86

POSITIVE LOGITS

AS

1.21

As

1.19

as

1.12

As

1.05

readAs

1.04

AS

0.85

 CreateTagHelper

0.82

ValueStyle

0.81

as

0.75

follows

0.74

Activations Density 0.360%

comparative phrases highlighting similarities or analogies

No Comments

No Known Activations