INDEX

Explanations

phrases indicating permission or allowance

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.10.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

ob

-0.65

 need

-0.54

obj

-0.50

writeByte

-0.48

hs

-0.47

 зай

-0.47

need

-0.46

 ра

-0.46

 canne

-0.45

 emplois

-0.44

POSITIVE LOGITS

 BorderRadius

0.91

 AssemblyCulture

0.87

 للمعارف

0.85

 يتيمه

0.83

SBATCH

0.82

 שוליים

0.76

errHandler

0.76

 Superhost

0.75

KommentareTeilen

0.74

mybatisplus

0.74

Activations Density 0.212%

phrases indicating permission or allowance

No Comments

No Known Activations