INDEX

Explanations

profanity and vulgar expressions

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 lähe

-0.68

 كومونز

-0.67

 Adagio

-0.66

 समीक्षक

-0.66

lewati

-0.66

 Bisch

-0.64

تفصیلات

-0.64

awtextra

-0.64

Gale

-0.63

,–

-0.62

POSITIVE LOGITS

fuck

1.10

 Fuck

1.09

 fuck

1.07

 fucking

1.06

FUCK

1.04

Fuck

1.03

 damn

1.01

 shit

1.00

 Fucking

0.99

 goddamn

0.98

Activations Density 0.142%

profanity and vulgar expressions

No Comments

No Known Activations