INDEX

Explanations

phrases related to personal identity and expressions of individuality

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

Contractions and abbreviations

np_acts-logits-general · gemini-2.0-flash

youve, Ive, dont, Generals

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

-0.58

$\

-0.54

principalTable

-0.53

and

-0.51

–

-0.50

Étienne

-0.49

ha

-0.48

Top

-0.48

POSITIVE LOGITS

 myſelf

1.17

 lenker

1.13

IsContent

1.12

 Majefty

1.11

 Jefus

1.10

Heres

1.10

ſelves

1.08

 youll

1.08

Efq

1.07

Theres

1.06

Activations Density 0.112%

phrases related to personal identity and expressions of individuality

Contractions and abbreviations

youve, Ive, dont, Generals

No Comments

No Known Activations