INDEX

Explanations

references to data retrieval or configuration loading in code

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

"from" in code or data structures

np_acts-logits-general · gemini-2.0-flash

from and to

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.18.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

-0.65

the

-0.65

so

-0.60

-0.58

as

-0.55

no

-0.54

an

-0.53

not

-0.51

“

-0.50

POSITIVE LOGITS

 CreateTagHelper

1.04

脚注の使い方

1.01

Viitteet

0.96

fromnode

0.94

AndEndTag

0.90

ChildScrollView

0.87

AddTagHelper

0.85

 AspNetCore

0.84

GEBURTSDATUM

0.82

Jof

0.81

Activations Density 0.163%

references to data retrieval or configuration loading in code

"from" in code or data structures

from and to

No Comments

No Known Activations