INDEX

Explanations

terms related to JSON data processing and serialization

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.15.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

RegressionTest

-0.75

oarece

-0.72

Tikang

-0.69

initis

-0.68

 noastre

-0.67

 assolutamente

-0.67

 Tilly

-0.66

PMailer

-0.64

moiselle

-0.63

دانشنامهٔ

-0.63

POSITIVE LOGITS

 json

1.36

json

1.28

 Json

1.27

 JSON

1.22

Json

1.14

JSON

1.01

ToJson

0.88

toJson

0.85

getJSON

0.84

fromJson

0.82

Activations Density 0.066%

terms related to JSON data processing and serialization

No Comments

No Known Activations