INDEX

Explanations

mentions of DNA and its related processes

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

DNA followed by biological descriptors

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 16-gemmascope-res-65k

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

65,536

Data Type

float32

Hook Name

blocks.16.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

keit

-0.63

 year

-0.60

hopper

-0.59

pede

-0.58

 Од

-0.58

lets

-0.57

 keer

-0.57

poin

-0.57

 Stron

-0.57

lings

-0.57

POSITIVE LOGITS

DNA

1.06

DNA

1.03

dna

0.90

LookAnd

0.84

ADN

0.77

НК

0.73

dna

0.72

 Isra

0.71

SequentialGroup

0.68

cifix

0.66

Activations Density 0.043%

mentions of DNA and its related processes

DNA followed by biological descriptors

No Comments

No Known Activations