INDEX

Explanations

segments of code or data that specify input and output operations

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.5.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

giphy

-0.68

ingway

-0.62

AddWithValue

-0.60

hazi

-0.58

 clearColor

-0.58

かわらず

-0.57

csolódó

-0.57

Aceite

-0.57

intahan

-0.56

SpringBootTest

-0.55

POSITIVE LOGITS

Autoritní

0.65

 Wikispecies

0.60

DebuggerNonUser

0.60

ViewFeatures

0.56

tagHelperRunner

0.56

setVerticalGroup

0.53

TypedDataSet

0.52

 Архивировано

0.50

 awakeFromNib

0.50

Activations Density 0.061%

segments of code or data that specify input and output operations

No Comments

No Known Activations