INDEX

Explanations

terms and phrases related to violence and conflict

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

ending in "der" or "ber"

np_acts-logits-general · gemini-2.0-flash

gender classification and murder

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.24.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

BufferException

-0.71

 latter

-0.69

-0.61

shel

-0.57

ArgumentParser

-0.57

%)$

-0.56

 litté

-0.54

UserScript

-0.52

sic

-0.51

 HttpNotFound

-0.51

POSITIVE LOGITS

ed

1.37

ized

1.35

ization

1.18

ised

1.07

ize

1.05

izing

0.94

izations

0.94

ous

0.84

isation

0.81

ific

0.81

Activations Density 0.424%

terms and phrases related to violence and conflict

ending in "der" or "ber"

gender classification and murder

No Comments

No Known Activations