INDEX

Explanations

elements related to programming functions and code execution

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

Tokens after punctuation marks

np_acts-logits-general · gemini-2.0-flash

technical terms and archaic spellings

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

<eos>

-0.59

 none

-0.41

and

-0.41

NOPQRST

-0.40

 with

-0.40

IND

-0.39

 just

-0.38

so

-0.37

 means

-0.36

zak

-0.36

POSITIVE LOGITS

 незавершена

1.17

 itſelf

0.94

 myſelf

0.88

 contextLoads

0.87

ſelf

0.83

 Monfieur

0.82

 ſche

0.80

 pleaſure

0.80

NUMX

0.79

хьтан

0.79

Activations Density 0.672%

elements related to programming functions and code execution

Tokens after punctuation marks

technical terms and archaic spellings

No Comments

No Known Activations