INDEX

Explanations

words and phrases indicating suitability or correctness

oai_token-act-pair · gemini-2.0-flash

appropriate

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

 appropriate

-2.02

appropriate

-1.74

Appropriate

-1.67

 relevant

-1.66

 Appropriate

-1.62

 suitable

-1.56

relevant

-1.45

Relevant

-1.36

 applicable

-1.26

suitable

-1.26

POSITIVE LOGITS

didSet

0.82

 CreateTagHelper

0.73

ergies

0.73

 EconPapers

0.72

enderror

0.71

InjectAttribute

0.71

AndEndTag

0.71

LabelTagHelper

0.70

MockBean

0.70

windowFixed

0.70

Activations Density 6.586%

words and phrases indicating suitability or correctness

appropriate

No Comments

No Known Activations