INDEX

Explanations

references to portions or components of larger entities or processes

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.6.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

 SwitchCompat

-0.89

 Majefty

-0.78

KommentareTeilen

-0.78

 Roskov

-0.75

moveToFirst

-0.74

 FetchType

-0.73

 fubject

-0.72

 Theſe

-0.71

ScopeManager

-0.71

 NSCoder

-0.71

POSITIVE LOGITS

 partly

0.64

partly

0.61

 Partly

0.58

 partially

0.53

Partly

0.53

 parcel

0.50

 parte

0.49

parcel

0.49

 parcialmente

0.45

 anse

0.45

Activations Density 0.466%

references to portions or components of larger entities or processes

No Comments

No Known Activations