INDEX

Explanations

terms related to cookies and previews

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

New Auto-Interp

Top Features by Cosine Similarity

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

Configuration

google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.2.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

IntoConstraints

-0.83

 كومونز

-0.76

 فريبيس

-0.72

 rowspan

-0.67

 onOptions

-0.67

EnableWeb

-0.63

letzt

-0.62

 varargin

-0.60

первых

-0.59

SequentialGroup

-0.58

POSITIVE LOGITS

axel

0.58

]->

0.58

Przypisy

0.56

eby

0.56

isand

0.55

mtd

0.54

 Viana

0.54

lenie

0.54

raisal

0.53

avadoc

0.53

Activations Density 0.040%

terms related to cookies and previews

No Comments

No Known Activations