INDEX

Explanations

terms related to network connections and protocols

oai_token-act-pair · gpt-4o-mini

Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.7.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Negative Logits

ArgsConstructor

-0.65

Expose

-0.53

uxxxx

-0.50

viewDidLoad

-0.48

GITHUB

-0.48

addCriterion

-0.47

expose

-0.47

tgz

-0.47

NOPQRST

-0.47

 Coaster

-0.46

POSITIVE LOGITS

parsedMessage

0.63

InvalidProtocol

0.63

 communications

0.61

bufio

0.59

MethodManager

0.59

 socket

0.59

socket

0.59

ResponseWriter

0.57

 communication

0.56

 FetchType

0.56

Activations Density 0.606%

terms related to network connections and protocols

No Known Activations