INDEX

Explanations

parts of code, court documents with citations, and for the word "for.'

oai_token-act-pair · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_4/width_16k/average_l0_88

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.4.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

OPSIS

-0.59

ValueGenerated

-0.51

<-

-0.51

onAttach

-0.50

الصفحه

-0.48

 LUMP

-0.47

medriver

-0.47

zoon

-0.47

HasOne

-0.47

rewsbury

-0.47

POSITIVE LOGITS

 Majefty

0.88

 myſelf

0.82

 pleaſure

0.78

 Monfieur

0.77

 ſeveral

0.75

 poffible

0.75

 picioare

0.75

 himſelf

0.72

 fevere

0.72

 zelve

0.71

Activations Density 2.658%

parts of code, court documents with citations, and for the word "for.'

No Comments

No Known Activations