INDEX

Explanations

sections that summarize findings and conclusions in research documentation

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_14/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.14.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

endphp

-0.78

-0.70

mybatisplus

-0.68

Архівовано

-0.64

COUVER

-0.63

醐

-0.62

 IBOutlet

-0.62

CppMethod

-0.61

Décès

-0.59

BindingResult

-0.59

POSITIVE LOGITS

↵

0.66

↵↵

0.63

ysaccharides

0.58

RegressionTest

0.57

 referenties

0.56

0.55

<eos>

0.54

holdet

0.54

 typelib

0.51

uxxxx

0.48

Activations Density 0.289%

sections that summarize findings and conclusions in research documentation

No Comments

No Known Activations