INDEX

Explanations

terms related to protocols in software or networking contexts

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.0.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

 AssemblyProduct

-0.98

complexContent

-0.95

niająca

-0.93

 Majefty

-0.92

 mergeFrom

-0.90

 Houſe

-0.87

 useAppContext

-0.84

webElementXpaths

-0.83

 itſelf

-0.82

AndroidJUnit

-0.82

POSITIVE LOGITS

protocol

0.90

Protocol

0.86

 protocol

0.83

proto

0.83

pic

0.79

 Protocol

0.78

pic

0.78

 protocols

0.72

 proto

0.71

PROTOCOL

0.71

Activations Density 0.147%

terms related to protocols in software or networking contexts

No Comments

No Known Activations