INDEX

Explanations

a variety of words relating to a wide variety of topics.

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

<bos>

-0.92

↵

-0.45

板

-0.43

edar

-0.39

設置

-0.38

var

-0.38

ked

-0.37

不成

-0.36

 equipe

-0.36

POSITIVE LOGITS

 nakalista

0.87

PerformLayout

0.82

RTEE

0.73

setViewportView

0.70

0.69

 resourceCulture

0.68

esModule

0.68

detectChanges

0.67

setVerticalGroup

0.67

 Insee

0.66

Activations Density 18.344%

a variety of words relating to a wide variety of topics.

No Comments

No Known Activations