INDEX

Explanations

comparative phrases and expressions that indicate similarity or contrast

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

SequentialGroup

-0.77

 purpoſe

-0.72

zerne

-0.69

 raiſ

-0.69

PhysRevLett

-0.68

dersfield

-0.66

 themſelves

-0.66

 edelstahl

-0.64

 himſelf

-0.63

 myſelf

-0.63

POSITIVE LOGITS

 like

1.21

like

1.07

Like

1.03

 Like

1.03

 resembled

0.96

 resembles

0.95

 resemble

0.95

 LIKE

0.93

 resembling

0.90

 akin

0.86

Activations Density 0.316%

comparative phrases and expressions that indicate similarity or contrast

No Comments

No Known Activations