INDEX

Explanations

phrases and expressions that indicate precision and specificity in statements

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.12.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

webElementXpaths

-0.46

enius

-0.45

󠁢

-0.44

 endwhile

-0.43

 RouterModule

-0.42

 AppCompatTheme

-0.42

ψ

-0.40

 Wiktionnaire

-0.38

nonzero

-0.38

endwhile

-0.38

POSITIVE LOGITS

 насељу

0.80

DoubleQuotes

0.79

 raczej

0.76

ebenarnya

0.73

 egentligen

0.71

 inkább

0.70

 jsPsych

0.69

 vielmehr

0.69

andExpect

0.69

 الحره

0.68

Activations Density 0.458%

phrases and expressions that indicate precision and specificity in statements

No Comments

No Known Activations