INDEX

Explanations

names and their affiliations or contexts in academic references

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

DeleteBehavior

-0.78

webElementXpaths

-0.76

ValueStyle

-0.75

 nakalista

-0.74

TypedDataSet

-0.71

Tembelea

-0.67

Personensuche

-0.64

migrationBuilder

-0.63

creativecommons

-0.62

хьтан

-0.61

POSITIVE LOGITS

 MonoBehaviour

0.66

سطس

0.58

itures

0.58

iasis

0.56

 Orpheus

0.51

 pearls

0.50

 Egli

0.50

 AspNetCore

0.49

 Athenians

0.49

useState

0.49

Activations Density 0.515%

names and their affiliations or contexts in academic references

No Comments

No Known Activations