INDEX

Explanations

terms related to API requests and responses

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

 Cowan

-0.68

 Matsu

-0.60

EndOf

-0.59

Errorf

-0.58

 Thal

-0.58

FORMAN

-0.57

 tocado

-0.57

thol

-0.56

 Tula

-0.56

addContainerGap

-0.56

POSITIVE LOGITS

Request

1.53

 Request

1.23

getRequest

1.17

 getRequest

1.10

requestCode

1.08

 HttpRequest

0.93

ItemBackground

0.90

HttpRequest

0.90

GetRequest

0.85

REQUEST

0.83

Activations Density 0.061%

terms related to API requests and responses

No Comments

No Known Activations