INDEX

Explanations

mentions of someone doing things in different time periods

oai_token-act-pair · gemini-2.0-flash

words related to performance or roles

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

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ValueStyle

-0.65

LookAnd

-0.59

 дописавши

-0.57

principalColumn

-0.56

CompleteListener

-0.54

contentLoaded

-0.53

 chi̍t

-0.51

 Affiliations

-0.50

@[+][

-0.50

 doInBackground

-0.49

POSITIVE LOGITS

 ANCHE

0.56

ثيق

0.56

verwijspagina

0.56

assertArray

0.56

fig

0.54

 appeared

0.54

appeared

0.52

 received

0.51

itiers

0.50

ograd

0.50

Activations Density 0.387%

mentions of someone doing things in different time periods

words related to performance or roles

No Comments

No Known Activations