INDEX

Explanations

code snippets or technical documentation in languages other than English

oai_token-act-pair · gemini-2.0-flash

multiple languages

np_max-act-logits · gemini-2.0-flash

say "▁"

np_max-act-logits · gpt-5-mini Triggered by @chenshw0109

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_25/width_16k/average_l0_41

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

 Italij

-0.44

ButterKnife

-0.40

 剪影

-0.36

 Monfieur

-0.35

 AssemblyCompany

-0.35

 特写

-0.34

 Shakspeare

-0.34

 becauſe

-0.34

 ſeveral

-0.33

 图解

-0.33

POSITIVE LOGITS

osoba

0.74

Rüyada

0.65

ook

0.64

دانشنامهٔ

0.64

nog

0.63

Een

0.63

gemeester

0.60

 donc

0.60

 auch

0.60

een

0.59

Activations Density 5.389%

code snippets or technical documentation in languages other than English

multiple languages

say "▁"

No Comments

No Known Activations