INDEX

Explanations

storage-related operations in a programming context

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 trajets

-0.54

 Głów

-0.52

,…

-0.46

 murs

-0.46

...:

-0.46

…,

-0.45

ittäin

-0.45

umahan

-0.44

 doInBackground

-0.43

 following

-0.43

POSITIVE LOGITS

dafx

0.80

AntiForgeryToken

0.75

richTextPanel

0.75

SourceChecksum

0.71

MessageOf

0.69

InjectAttribute

0.67

 noDo

0.66

setVerticalGroup

0.65

 تضيفلها

0.65

elemField

0.62

Activations Density 0.236%

storage-related operations in a programming context

No Comments

No Known Activations