INDEX

Explanations

queries related to data manipulation and error handling in programming or databases

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

albeit

-0.89

وردار

-0.86

 nonché

-0.84

setVerticalGroup

-0.83

 albeit

-0.81

 whatnot

-0.80

 lenker

-0.80

 saurait

-0.79

 tantôt

-0.78

 ThemeData

-0.78

POSITIVE LOGITS

 informations

0.66

 maybe

0.63

 serius

0.60

 inmig

0.58

 realy

0.57

 analisis

0.57

 imposible

0.56

 Maybe

0.54

 begin

0.54

 standart

0.54

Activations Density 1.031%

queries related to data manipulation and error handling in programming or databases

No Comments

No Known Activations