INDEX

Explanations

words and phrases that indicate that a topic is being presented

oai_token-act-pair · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_19/width_16k/average_l0_12

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.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

 positive

-1.26

 negative

-1.19

 Positive

-1.16

positive

-1.09

Positive

-1.08

Negative

-1.08

negative

-1.07

 Negative

-1.05

 POSITIVE

-1.03

 NEGATIVE

-0.91

POSITIVE LOGITS

ScopeManager

0.65

 betweenstory

0.58

isContained

0.57

 szóci

0.53

PRWEB

0.52

 useRef

0.52

 TextAppearance

0.51

DrawerToggle

0.50

ThroughAttribute

0.50

Hochspringen

0.49

Activations Density 1.191%

words and phrases that indicate that a topic is being presented

No Comments

No Known Activations