INDEX

Explanations

medical terms and references related to case studies or reports

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

Tokens appearing before journal names

np_acts-logits-general · gemini-2.0-flash

names of scientific journals

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

 stället

-0.49

 negli

-0.45

 singoli

-0.45

 steder

-0.45

 paraître

-0.44

puh

-0.43

 kuni

-0.43

 vân

-0.42

र्थ

-0.42

ं

-0.42

POSITIVE LOGITS

 disambiguazione

0.93

 doInBackground

0.84

 typelib

0.78

WriteTagHelper

0.77

 AssemblyCulture

0.77

 ویکی‌پدی

0.76

 snippetHide

0.75

complexContent

0.72

LookAnd

0.71

OGND

0.69

Activations Density 0.190%

medical terms and references related to case studies or reports

Tokens appearing before journal names

names of scientific journals

No Comments

No Known Activations

medical terms and references related to case studies or reports

Tokens appearing before journal names

names of scientific journals

No Comments

No Known Activations