INDEX

Explanations

references to functional programming or scripting

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

complexType

-0.59

zzleHttp

-0.53

InvalidProtocol

-0.51

protoimpl

-0.47

sendRedirect

-0.47

 szerint

-0.47

MMdd

-0.46

 gainera

-0.45

 profundos

-0.44

ppins

-0.44

POSITIVE LOGITS

还好

0.77

SequentialGroup

0.77

 okay

0.73

ok

0.67

but

0.65

没问题

0.65

 alright

0.65

 certes

0.64

OK

0.64

 normal

0.63

Activations Density 0.323%

references to functional programming or scripting

No Comments

No Known Activations