INDEX

Explanations

programming-related keywords and structures, particularly in the context of API interactions and generated 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

AccessorTable

-0.68

regas

-0.58

 onPostExecute

-0.54

PhysRev

-0.53

aboo

-0.52

laşı

-0.52

SOR

-0.51

alina

-0.51

 faculty

-0.51

жар

-0.51

POSITIVE LOGITS

حياته

0.84

sizeCache

0.65

ⓧ

0.65

 Signalez

0.62

 estekak

0.60

SharedDtor

0.59

dAtA

0.59

 ProtoMessage

0.59

 yyhl

0.57

 Wicidata

0.55

Activations Density 0.386%

programming-related keywords and structures, particularly in the context of API interactions and generated code

No Comments

No Known Activations