INDEX

Explanations

code snippets relating to data manipulation and reshaping in arrays

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Personendaten

-0.74

 ligiloj

-0.66

ագրություններ

-0.60

 فريبيس

-0.58

typeorm

-0.58

gridx

-0.54

 Meksiku

-0.53

 BorderRadius

-0.53

AndEndTag

-0.52

bootstrapcdn

-0.51

POSITIVE LOGITS

 axis

0.81

axis

0.70

 createSlice

0.64

Axis

0.63

 Axis

0.58

 WaitForSeconds

0.57

">//

0.56

 AXIS

0.55

GetAxis

0.54

 moindre

0.54

Activations Density 0.080%

code snippets relating to data manipulation and reshaping in arrays

No Comments

No Known Activations