INDEX

Explanations

specific terms and phrases related to genetics and mutations

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

Tokens followed by "and"

np_acts-logits-general · gemini-2.0-flash

mathematical and code contexts

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-16k

Configuration

google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

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

-0.64

-0.57

↵↵

-0.51

<eos>

-0.51

-0.50

-0.49

-0.48

-0.47

is

-0.46

POSITIVE LOGITS

 ProtoMessage

1.04

 كومونز

0.99

queryInterface

0.95

ReusableCell

0.94

Efq

0.93

 transfieras

0.93

 myſelf

0.90

 estekak

0.88

 المعيارى

0.88

তথ্যসূত্র

0.87

Activations Density 0.716%

specific terms and phrases related to genetics and mutations

Tokens followed by "and"

mathematical and code contexts

No Comments

No Known Activations