INDEX

Explanations

profanity and strong emotional expressions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_9/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.9.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

 كومونز

-0.69

তথ্যসূত্র

-0.68

ExtendWith

-0.66

lewati

-0.66

ductory

-0.65

Gale

-0.64

>");

-0.60

intptr

-0.60

ství

-0.60

,–

-0.59

POSITIVE LOGITS

 fucking

1.31

fuck

1.26

fucking

1.24

FUCK

1.19

 goddamn

1.19

 Fuck

1.18

 Fucking

1.16

Fuck

1.16

 bullshit

1.16

 fuckin

1.15

Activations Density 0.201%

profanity and strong emotional expressions

No Comments

No Known Activations