INDEX

Explanations

mentions of studies from the CDC

oai_token-act-pair · gemini-2.0-flash

technical terms and specific data identifiers

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

scientific reports

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

Not in Any Lists

No Comments

Negative Logits

 prostagland

-0.45

zeptember

-0.42

 Wynne

-0.41

 eukary

-0.41

خاذ

-0.40

 закреп

-0.39

concurrency

-0.39

schema

-0.39

 prokary

-0.39

gener

-0.39

POSITIVE LOGITS

IsContent

0.90

principalTable

0.88

msgTypes

0.85

matchCondition

0.82

 صوتيه

0.80

ConstraintMaker

0.78

Liên

0.76

Personensuche

0.75

GraphicsUnit

0.74

AddTagHelper

0.74

Activations Density 1.097%

mentions of studies from the CDC

technical terms and specific data identifiers

scientific reports

No Comments

No Known Activations