INDEX

Explanations

references to specific types of nerves and nerve injuries

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

nerve root block

np_acts-logits-general · gemini-2.5-flash-lite

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k

Configuration

google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

131,072

Data Type

float32

Hook Name

blocks.9.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

googleapis

-0.49

 Chico

-0.49

 تكبرها

-0.49

日閲覧

-0.49

Poz

-0.47

Chico

-0.46

DOCTYPE

-0.45

XXL

-0.45

 Puri

-0.44

ɵɵ

-0.44

POSITIVE LOGITS

 nerve

2.17

 Nerve

2.05

 nerves

1.41

 Nerven

1.28

 nerv

1.13

 nervios

1.05

 нер

0.96

 Nerv

0.90

nerv

0.87

神経

0.85

Activations Density 0.006%

references to specific types of nerves and nerve injuries

nerve root block

No Comments

No Known Activations