INDEX

Explanations

a variety of terms related to messaging, political figures/events, and technical/financial reports.

oai_token-act-pair · gemini-2.0-flash

servers and legal cases

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

횟

-0.68

UnusedPrivate

-0.67

SpringRunner

-0.67

zzleHttp

-0.64

 microbiome

-0.64

NewUrlParser

-0.64

 "..\..\..\

-0.63

 COVID

-0.62

<bos>

-0.60

riors

-0.60

POSITIVE LOGITS

 InputDecoration

0.53

itself

0.51

 vérit

0.51

 pitié

0.49

 themselves

0.48

 himself

0.47

 habet

0.47

 Bewußt

0.47

 vectoriales

0.47

 Chwiliwch

0.47

Activations Density 10.125%

a variety of terms related to messaging, political figures/events, and technical/financial reports.

servers and legal cases

No Comments

No Known Activations

a variety of terms related to messaging, political figures/events, and technical/financial reports.

servers and legal cases

No Comments

No Known Activations