INDEX

Explanations

references to time, specifically days, months and years

oai_token-act-pair · gemini-2.0-flash

temporal adverbs

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

earlier or later

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

RenderAtEndOf

-0.69

uesia

-0.67

kháu

-0.65

 يتيمه

-0.64

setVerticalGroup

-0.64

Personendaten

-0.63

NameInMap

-0.63

<?

-0.62

 lenker

-0.62

InitVars

-0.62

POSITIVE LOGITS

 that

0.62

 nakalista

0.56

 consultato

0.55

in

0.52

GeoNames

0.51

igur

0.50

Dislikes

0.48

 profiles

0.48

breasted

0.48

ApiOperation

0.47

Activations Density 7.825%

references to time, specifically days, months and years

temporal adverbs

earlier or later

No Comments

No Known Activations