INDEX

Explanations

terms related to data processing and transformation, particularly in the context of deserialization and modifying data formats

oai_token-act-pair · gpt-4o-mini

New Auto-Interp

Configuration

chanind/gemma-2-2b-batch-topk-matryoshka-saes-w-32k-l0-40/standard/blocks.12.hook_resid_post

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

32,768

Data Type

float32

Hook Name

blocks.12.hook_resid_post

Architecture

jumprelu

Context Size

1,024

Dataset

chanind/pile-uncopyrighted-gemma-1024-abbrv-1B

Embeds

IFrame

Link

Negative Logits

 فريبيس

-0.84

SceneManagement

-0.65

 NavController

-0.64

Tikang

-0.63

älde

-0.63

Bibliograf

-0.62

 Bundy

-0.61

HttpFoundation

-0.59

AutoScaleMode

-0.57

OPTIONS

-0.56

POSITIVE LOGITS

 unpacked

0.62

 unpack

0.59

 ProtoMessage

0.58

fromJson

0.57

Decoded

0.56

 decoding

0.56

Inflater

0.54

 unpacking

0.53

 Deserialize

0.52

decode

0.52

Activations Density 0.053%

terms related to data processing and transformation, particularly in the context of deserialization and modifying data formats

No Known Activations