INDEX

Explanations

names and significant individuals referenced in a narrative context

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

Surnames or last names

np_acts-logits-general · gemini-2.0-flash

names and possessives

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

 Inter

-0.51

ThemeOverlay

-0.51

mment

-0.50

ysuckle

-0.50

 Safe

-0.49

sal

-0.48

hetta

-0.48

inent

-0.48

neum

-0.47

jenost

-0.47

POSITIVE LOGITS

 himſelf

1.12

 himself

1.08

himself

0.84

 فريبيس

0.82

 Himself

0.82

 defaultstate

0.76

 myſelf

0.72

RenderAtEndOf

0.72

 stesso

0.70

 mwenye

0.68

Activations Density 0.241%

names and significant individuals referenced in a narrative context

Surnames or last names

names and possessives

No Comments

No Known Activations