INDEX

Explanations

start of class definitions

oai_token-act-pair · gemini-2.0-flash

abstract

np_max-act · 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

saraba

-0.66

Same

-0.61

 same

-0.58

……"

-0.57

webElementXpaths

-0.57

same

-0.57

 Same

-0.57

]),

-0.56

>(),

-0.53

AddTagHelper

-0.53

POSITIVE LOGITS

 myſelf

0.61

 supérieures

0.61

SBATCH

0.59

HostException

0.58

 supérieurs

0.56

crollView

0.55

 Theſe

0.54

dbo

0.53

Efq

0.52

 Allociné

0.52

Activations Density 1.886%

start of class definitions

abstract

No Comments

No Known Activations