INDEX

Explanations

the "sp" character combination

oai_token-act-pair · gemini-2.0-flash

words starting with 'sp'

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

sp

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

TagHelper

-0.70

AccessException

-0.43

CIV

-0.43

 الحره

-0.42

 Hals

-0.41

 deputy

-0.40

umpulkan

-0.40

Demografia

-0.39

estación

-0.39

 гг

-0.39

POSITIVE LOGITS

IsMutable

0.73

expandindo

0.70

ViewImports

0.69

IntoConstraints

0.68

 vermelhas

0.67

tvguidetime

0.66

netinet

0.66

enumi

0.65

 contextLoads

0.64

 OnTriggerEnter

0.63

Activations Density 0.311%

the "sp" character combination

words starting with 'sp'

sp

No Comments

No Known Activations