INDEX

Explanations

phrases indicating requests or actions, particularly in a programming or technical context

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

"input" or "field"

np_acts-logits-general · gemini-2.0-flash

text fields

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

AnchorTagHelper

-0.68

 ujednoznacz

-0.64

 createSlice

-0.60

ExtendWith

-0.58

listFiles

-0.55

 estekak

-0.53

createServer

-0.53

 Meksiku

-0.52

 onAnimation

-0.51

ніципа

-0.50

POSITIVE LOGITS

 input

1.43

 inputs

1.34

 Input

1.33

input

1.28

输入

1.27

Input

1.26

 Inputs

1.22

 INPUT

1.19

INPUT

1.16

 fields

1.15

Activations Density 0.292%

phrases indicating requests or actions, particularly in a programming or technical context

"input" or "field"

text fields

No Comments

No Known Activations