INDEX

Explanations

terms related to legal and procedural contexts, particularly concerning evidence and its implications

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

Whilst

-1.61

 Whilst

-1.50

initialise

-1.43

 enquiries

-1.36

 whilst

-1.35

 recognisable

-1.34

 realised

-1.34

 Enquiries

-1.33

Colour

-1.33

 standardised

-1.32

POSITIVE LOGITS

 confiable

1.23

ônicos

1.12

 neighborhoods

1.08

 flavorful

1.08

neighborhood

1.06

 neighborhood

1.05

 rumors

1.04

 aluminum

1.03

 neighbors

1.03

Neighbors

1.03

Activations Density 5.950%

terms related to legal and procedural contexts, particularly concerning evidence and its implications

No Comments

No Known Activations