INDEX

Explanations

references to education and professional qualifications

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k

Configuration

google/gemma-scope-9b-pt-res/layer_36/width_16k/average_l0_120

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.36.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 esso

-0.81

ньому

-0.68

 dets

-0.65

[]*

-0.44

 Оно

-0.44

 deles

-0.41

 оно

-0.39

父子

-0.38

 usarlo

-0.38

gevens

-0.38

POSITIVE LOGITS

she

3.83

 그녀

2.94

her

2.94

彼女は

2.61

 hennes

2.56

她

2.56

 její

2.55

彼女の

2.53

she

2.44

เธอ

2.39

Activations Density 1.835%

references to education and professional qualifications

No Comments

No Known Activations