INDEX

Explanations

words and phrases related to legal arguments or scientific evidence.

oai_token-act-pair · gemini-2.0-flash

variations of the word "support"

np_token-act-pair-logits · gpt-4o-mini

support

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

google/gemma-scope-2b-pt-transcoders/layer_21/width_16k/average_l0_13

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.21.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

CodeAttribute

-0.64

IntoConstraints

-0.63

 resourceCulture

-0.56

SourceChecksum

-0.56

 Вікіпе

-0.53

igshid

-0.53

":[{

-0.53

FormTagHelper

-0.52

setVerticalGroup

-0.52

MigrationBuilder

-0.52

POSITIVE LOGITS

 support

2.84

support

2.53

 Support

2.53

Support

2.45

 supports

2.38

 SUPPORT

2.36

 supporting

2.36

 supported

2.25

SUPPORT

2.20

 Supports

2.08

Activations Density 7.539%

words and phrases related to legal arguments or scientific evidence.

variations of the word "support"

support

No Comments

No Known Activations