INDEX

Explanations

details regarding study participation and selection bias

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.13.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

 оригіналу

-0.70

 AssemblyCulture

-0.69

httphttps

-0.59

WebElementEntity

-0.56

ⓧ

-0.56

Crush

-0.55

InlineData

-0.53

/>";

-0.52

 Cole

-0.50

ніципалі

-0.50

POSITIVE LOGITS

 nargin

0.56

 signifies

0.52

 الرياضيه

0.52

GEBURTSDATUM

0.51

 nakalista

0.50

 berarti

0.49

 significa

0.48

 indicative

0.48

を選

0.47

GenerationType

0.47

Activations Density 0.407%

details regarding study participation and selection bias

No Comments

No Known Activations