INDEX

Explanations

phrases that establish relationships or separations, particularly in a context of oppositional or contrasting ideas

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Efq

-0.85

 quæ

-0.85

XK

-0.83

 itſelf

-0.80

 Laplacian

-0.80

 pleaſure

-0.79

 purpoſe

-0.78

 Majefty

-0.76

 becauſe

-0.74

 abbildung

-0.74

POSITIVE LOGITS

OutOf

1.08

 outta

1.06

the

0.89

 INTO

0.87

 Into

0.86

 into

0.83

 Dooley

0.79

off

0.74

Into

0.73

out

0.73

Activations Density 0.034%

phrases that establish relationships or separations, particularly in a context of oppositional or contrasting ideas

No Comments

No Known Activations