INDEX

Explanations

instances of profanity or strong language

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

 Kenn

-0.53

bibitem

-0.52

 protoimpl

-0.52

 /\.(

-0.52

_(

-0.52

AxisAlignment

-0.52

Scot

-0.52

TagHelpers

-0.51

شهاد

-0.51

vs

-0.50

POSITIVE LOGITS

 shit

1.46

 Shit

1.35

 fuck

1.30

 SHIT

1.27

Fuck

1.27

shit

1.25

FUCK

1.24

fuck

1.19

Shit

1.19

 fucking

1.16

Activations Density 0.081%

instances of profanity or strong language

No Comments

No Known Activations