INDEX

Explanations

words and numbers related to business contracts and reports.

oai_token-act-pair · gemini-2.0-flash

Short abbreviations

np_max-act-logits · gemini-2.0-flash

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

 NSCoder

-0.58

interopRequire

-0.52

 jealousy

-0.51

StoryboardSegue

-0.50

 jsPsych

-0.49

ErrorListener

-0.48

 '\\;'

-0.47

 CARTOON

-0.46

 cynicism

-0.46

 sarcasm

-0.44

POSITIVE LOGITS

CEE

0.62

 Bucharest

0.56

IEC

0.56

MTS

0.55

IEC

0.55

FEC

0.53

apimachinery

0.53

NEV

0.52

MessageState

0.52

ESS

0.52

Activations Density 39.605%

words and numbers related to business contracts and reports.

Short abbreviations

No Comments

No Known Activations