INDEX

Explanations

words related to Facebook ads or users

oai_token-act-pair · gemini-2.0-flash

words related to advertising and customization

np_token-act-pair-logits · gpt-4o-mini

social media

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Negative Logits

 AssemblyCulture

-0.63

Jeografia

-0.63

 AspNetCore

-0.60

]--;

-0.59

 насељу

-0.58

 BorderSide

-0.57

 ویکی‌پدیای

-0.56

imetsu

-0.54

 '\\;'

-0.54

 Antar

-0.54

POSITIVE LOGITS

TagMode

0.51

 Secret

0.50

 Fresh

0.48

 feed

0.48

AddHtmlAttribute

0.47

atili

0.46

feed

0.45

 berta

0.45

Ter

0.45

vised

0.45

Activations Density 1.615%

words related to Facebook ads or users

words related to advertising and customization

social media

No Known Activations