INDEX

Explanations

language patterns indicating medical or health-related topics

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.11.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Efq

-0.81

ſelves

-0.77

 ſeveral

-0.75

 myſelf

-0.75

 pleaſure

-0.73

 ſmall

-0.72

ſelf

-0.70

 ſta

-0.69

 faſt

-0.68

 tfsi

-0.67

POSITIVE LOGITS

之一

0.49

 pourriez

0.45

 ever

0.45

 rett

0.44

 Tatsache

0.43

nocześnie

0.43

INSTALLED

0.43

 totalité

0.42

 widest

0.42

doctype

0.41

Activations Density 0.365%

language patterns indicating medical or health-related topics

No Comments

No Known Activations