INDEX

Explanations

assertions or claims about health and wellness

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.23.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

ômico

-0.79

 computadora

-0.79

 esposo

-0.78

Someday

-0.77

 confiable

-0.74

 computadoras

-0.74

ighborhood

-0.74

 someday

-0.73

 neighborhood

-0.73

σθαι

-0.72

POSITIVE LOGITS

Whilst

1.97

 Whilst

1.88

 whilst

1.66

initialise

1.39

Firstly

1.29

 Firstly

1.29

£

1.17

 recognising

1.14

 realising

1.10

 firstly

1.09

Activations Density 0.400%

assertions or claims about health and wellness

No Comments

No Known Activations