INDEX

Explanations

elements related to programming logic and structure within code

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

最快更新

-0.61

Mediabestanden

-0.61

ecutive

-0.59

gida

-0.59

\{\\

-0.57

InstrumentedTest

-0.57

obenzene

-0.56

 خارجية

-0.54

awaiter

-0.54

kman

-0.54

POSITIVE LOGITS

 CreateTagHelper

0.59

 StringTokenizer

0.57

Referències

0.55

 resourceCulture

0.54

NameValuePair

0.53

UnusedPrivate

0.53

DMR

0.50

 localObject

0.50

 '\\;'

0.48

voorbeeld

0.47

Activations Density 0.165%

elements related to programming logic and structure within code

No Comments

No Known Activations