INDEX

Explanations

instances of the word "modify" and its variations to indicate adjustments or alterations

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

Tokens related to "modify" or "modifying"

np_acts-logits-general · gemini-2.0-flash

modify

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

lossians

-0.50

åk

-0.48

ंदीखरीदारी

-0.48

 ErrIntOverflow

-0.47

XLV

-0.45

UALA

-0.45

routeProvider

-0.45

NamedQuery

-0.45

 altında

-0.45

POSITIVE LOGITS

 modifying

0.95

 modifies

0.94

 modify

0.93

 Modify

0.92

 modification

0.90

 modifications

0.90

 Modif

0.89

 modif

0.86

 修正

0.85

 Modification

0.84

Activations Density 0.409%

instances of the word "modify" and its variations to indicate adjustments or alterations

Tokens related to "modify" or "modifying"

modify

No Comments

No Known Activations