INDEX

Explanations

a set of very common words such as forms of "to be", conjunctions, and prepositions.

oai_token-act-pair · gemini-2.0-flash

negative movie reviews

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

is/was/are

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

WriteBarrier

-0.65

ValueStyle

-0.62

كويكب

-0.60

adpleegd

-0.59

WriteTagHelper

-0.58

twimg

-0.56

ScopeManager

-0.56

最快更新

-0.56

 Fost

-0.55

 وتسجيلات

-0.55

POSITIVE LOGITS

 dreadful

0.54

 awful

0.54

 poor

0.52

 fine

0.52

 horrible

0.50

 worst

0.50

 terrible

0.50

awful

0.49

 wretched

0.49

 noDo

0.48

Activations Density 1.244%

a set of very common words such as forms of "to be", conjunctions, and prepositions.

negative movie reviews

is/was/are

No Comments

No Known Activations