INDEX

Explanations

words that express opinions or judgements, often with qualifiers.

oai_token-act-pair · gemini-2.0-flash

Blog/conversational text

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_6/width_16k/average_l0_95

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.6.ln2.hook_normalized

Architecture

jumprelu_transcoder

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Negative Logits

MLLoader

-0.44

viewWillAppear

-0.43

JsonIgnore

-0.43

وأضاف

-0.42

cticide

-0.42

τία

-0.40

 Jolie

-0.40

pital

-0.40

aryti

-0.40

OTE

-0.39

POSITIVE LOGITS

IntoConstraints

0.83

AlterField

0.77

findpost

0.64

 Audiodateien

0.63

 PhpStorm

0.63

 SafeMath

0.61

 Qaraldi

0.58

soort

0.58

 Архів

0.58

richTextPanel

0.57

Activations Density 21.755%

words that express opinions or judgements, often with qualifiers.

Blog/conversational text

No Known Activations