INDEX

Explanations

expressions of frustration or contempt directed towards individuals or groups

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

Negative sentiment/name-calling

np_acts-logits-general · gemini-2.0-flash

insults and prejudiced language

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.22.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

guien

-0.60

 löyty

-0.58

 saites

-0.57

 ſever

-0.57

=$?

-0.55

 SEDS

-0.55

]--;

-0.55

 يتيمه

-0.54

]}

-0.52

 auffi

-0.51

POSITIVE LOGITS

 stupid

1.11

 bitch

1.10

 idiot

1.09

 bastard

1.07

 asshole

1.06

 scum

1.05

 bastards

1.02

 worthless

1.00

 idiots

0.98

 dumbass

0.98

Activations Density 0.298%

expressions of frustration or contempt directed towards individuals or groups

Negative sentiment/name-calling

insults and prejudiced language

No Comments

No Known Activations

expressions of frustration or contempt directed towards individuals or groups

Negative sentiment/name-calling

insults and prejudiced language

No Comments

No Known Activations