INDEX

Explanations

HTML code and words related to navigation bars

oai_token-act-pair · gemini-2.0-flash

variations of the word "link"

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

links

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

ResumeLayout

-0.51

saraba

-0.46

 /*#__

-0.44

 inflo

-0.44

DispatchToProps

-0.43

 gebo

-0.43

#+#

-0.43

 carbonate

-0.43

 elliptical

-0.43

ouble

-0.42

POSITIVE LOGITS

 links

1.06

 Links

1.02

links

0.91

Links

0.91

 LINKS

0.84

 link

0.78

 linking

0.75

 enlaces

0.75

LINKS

0.75

 kasarigan

0.73

Activations Density 2.117%

HTML code and words related to navigation bars

variations of the word "link"

links

No Comments

No Known Activations