INDEX

Explanations

references to changes, updates, and modifications in texts or systems

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

PhysRevD

-0.66

 '\\;'

-0.61

 Redu

-0.54

Inser

-0.52

 erhöhen

-0.51

stract

-0.50

 Reduction

-0.49

Owned

-0.48

 création

-0.48

 verzichten

-0.48

POSITIVE LOGITS

 modified

1.14

 expanded

1.03

 upgraded

1.01

 improved

0.99

 extended

0.99

 altered

0.98

 amended

0.96

 revised

0.94

 tweaked

0.94

 changed

0.94

Activations Density 0.956%

references to changes, updates, and modifications in texts or systems

No Comments

No Known Activations