INDEX

Explanations

instructions or parameters related to data input and processing

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

 garcía

-0.68

 sérieux

-0.61

ksessa

-0.58

 trouva

-0.54

 gordo

-0.53

 newItem

-0.53

 honnête

-0.51

 pauvre

-0.50

 plonge

-0.49

KommentareTeilen

-0.49

POSITIVE LOGITS

 irrespective

0.74

Hence

0.71

 atleast

0.71

 upto

0.70

respective

0.70

userdetails

0.70

upto

0.68

noOf

0.67

 noOf

0.67

 hence

0.67

Activations Density 0.781%

instructions or parameters related to data input and processing

No Comments

No Known Activations