INDEX

Explanations

terms related to preservation and maintaining original characteristics

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

describing maintaining original condition

np_acts-logits-general · gemini-2.0-flash

preserving original state

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

migrationBuilder

-0.63

 newState

-0.57

JspWriter

-0.56

NewUrlParser

-0.56

出版年

-0.55

äte

-0.54

 wireType

-0.54

protoimpl

-0.54

offsetof

-0.53

POSITIVE LOGITS

 original

0.95

 intact

0.92

original

0.86

Original

0.82

ORIGINAL

0.81

 retains

0.81

 integrity

0.80

 unchanged

0.80

 Original

0.74

 preserving

0.73

Activations Density 0.357%

terms related to preservation and maintaining original characteristics

describing maintaining original condition

preserving original state

No Comments

No Known Activations