INDEX

Explanations

terms and references related to HTTP 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 @ 20-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.20.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

VersionUID

-0.65

isContained

-0.63

noin

-0.53

pur

-0.52

@[+][

-0.51

וויק

-0.47

oredCriteria

-0.46

roupa

-0.46

 skon

-0.45

 MonoBehaviour

-0.45

POSITIVE LOGITS

riezmann

0.69

calciatore

0.59

ttps

0.57

 nhiêu

0.57

PhysRev

0.57

ioutil

0.57

╔

0.56

 rêver

0.55

currentColor

0.54

igshid

0.53

Activations Density 0.067%

terms and references related to HTTP requests and responses

No Comments

No Known Activations