INDEX

Explanations

references to the absence of something or negation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

ward

-0.72

brainly

-0.70

 Praça

-0.67

 buhay

-0.65

ategy

-0.65

 Draper

-0.65

ạm

-0.65

WireFormatLite

-0.65

BPI

-0.64

paraíso

-0.63

POSITIVE LOGITS

 none

2.05

none

1.91

None

1.78

 None

1.76

 NONE

1.71

NONE

1.70

 ninguno

1.51

 nessuno

1.14

nobody

1.00

 nobody

0.97

Activations Density 0.053%

references to the absence of something or negation

No Comments

No Known Activations