INDEX

Explanations

repeated elements or objects within a set

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.3.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

UrlResolution

-0.84

SequentialGroup

-0.75

AndEndTag

-0.71

httphttps

-0.69

Aholisi

-0.68

 ModelExpression

-0.67

 ListNode

-0.64

Véxase

-0.64

 Whigs

-0.62

 विश्वसनीयता

-0.62

POSITIVE LOGITS

={()=>

0.61

зумі

0.54

ordnungen

0.51

pel

0.51

[:,:,

0.49

 noDo

0.48

PreferredItem

0.48

per

0.48

So

0.48

 thread

0.47

Activations Density 0.119%

repeated elements or objects within a set

No Comments

No Known Activations