INDEX

Explanations

terms associated with API responses and requests

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

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.1.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

 متعلقه

-0.78

Ko

-0.56

 applied

-0.55

 spô

-0.54

 Mathf

-0.54

enzie

-0.53

CU

-0.51

 Tiefe

-0.51

 affecting

-0.51

 apply

-0.50

POSITIVE LOGITS

 ProtoMessage

0.83

HTTPResponse

0.81

 ResponseEntity

0.79

Response

0.78

ResponseWriter

0.78

RectangleBorder

0.77

response

0.76

 Responses

0.73

 responses

0.71

Responses

0.71

Activations Density 0.175%

terms associated with API responses and requests

No Comments

No Known Activations