INDEX

Explanations

elements related to graphical object manipulation and positioning in programming

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.25.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

RenderAtEndOf

-0.59

ConstraintMaker

-0.58

ագրություններ

-0.58

 surla

-0.57

TypedDataSet

-0.56

orianCalendar

-0.55

clusal

-0.54

Vidite

-0.54

ällor

-0.54

 dAtA

-0.53

POSITIVE LOGITS

0.79

 horizontal

0.76

0.75

0.73

0.70

横

0.68

 Horizontal

0.66

horizontal

0.66

vx

0.66

 longitude

0.65

Activations Density 0.373%

elements related to graphical object manipulation and positioning in programming

No Comments

No Known Activations